Vibe Coding DiscoverCategory
AI Tools
Developer tools for evaluation, observability, and AI operations.
| Project name | Stars | Category | Language | Tags | Summary | View Project |
|---|---|---|---|---|---|---|
| SemIf-OpenJev | ★ 4.2K | AI Tools | Python | semantic decisions · direct logits · open models · model inference · probability calibration · decision scoring · benchmarking · WebGPU | Python tool for scoring runtime-defined semantic decisions with open models. It reads option probabilities directly from model logits, with calibration and direct, cached, and parallel scoring modes; includes PyTorch, MLX, llama.cpp, and browser demos. | View Project → |
| Model-Optimizer | ★ 3.9K | AI Tools | Python | model optimization · quantization · post-training quantization · quantization-aware training · pruning · distillation · speculative decoding · sparsity · neural architecture search · inference acceleration · model compression | Python library for optimizing PyTorch, Hugging Face, and ONNX models with quantization, pruning, distillation, sparsity, NAS, and speculative decoding. Exports optimized checkpoints for deployment with TensorRT-LLM, TensorRT, vLLM, and SGLang. | View Project → |
| open-higgsfield | ★ 3.8K | AI Tools | TypeScript | image-generation · video-generation · generative-ai · studio-ui · prompt-composer · gallery · batch-generation · self-hosted · nextjs · zustand · vercel-blob · indexeddb · model-catalog · media-uploads · open-source · byok | Open-source self-hosted studio for image and video generation: one prompt bar drives 38 models (8 image, 30 video) with per-model settings, media inputs, batch runs, and a gallery with history, reuse, and bulk actions. Uses your own platform key via server actions. | View Project → |
| SemIf | ★ 3.6K | AI Tools | Python | semantic-decisions · logit-readout · llm-inference · classification · benchmarking · agents · webgpu · gguf · quantization · evaluation · probability-calibration · reranking · pytorch · reproducibility · local-gpu · runtime-criteria | SemIf reads typed option probabilities directly from open LLM logits to answer runtime-defined decisions (routing, retries, evidence checks) without generating or parsing text. Includes Python CLI, frozen benchmarks, and a WebGPU browser demo on 4B-class models. | View Project → |
| Observal | ★ 3.6K | AI Tools | Python | mcp · agents · skills · registry · self-hosted · observability · insights · cli · session-replay · governance · llm-ops · claude-code · cursor · codex · hooks · prompts | Self-hosted control plane and registry for internal AI components: bundle skills, MCP servers, hooks, prompts and sandboxes into versioned agents, install them into Claude Code/Cursor/Codex and other harnesses, and get insight reports plus session replay from real usage data. | View Project → |
| evalscope | ★ 3.5K | AI Tools | Python | LLM evaluation · benchmarking · performance testing · VLM evaluation · RAG evaluation · agent evaluation · multimodal · model comparison · evaluation reports · load testing | EvalScope is a Python framework for evaluating LLM, vision-language, embedding, reranking, and generative models. It includes benchmark integrations, RAG and agent evaluation, inference load testing, and a dashboard for comparing results. | View Project → |
| Clypra | ★ 3.3K | AI Tools | TypeScript | video-editor · tauri-v2 · react-19 · rust · typescript · wgpu · ffmpeg · gpu-acceleration · timeline · desktop-app · cross-platform · capacitor · media-tooling · open-source · mit-license | Clypra is a free MIT-licensed desktop video editor built with Rust, Tauri v2, and React 19, using FFmpeg plus hardware GPU decoding (VideoToolbox/D3D11VA/VAAPI) for sub-10ms frame decode and a frame-accurate multi-track timeline. It is a media/creative tool, not an AI, agent, or LLM project. | View Project → |
| Switchyard | ★ 3.2K | AI Tools | Rust | llm-routing · model-routing · llm-gateway · openai-compatible · anthropic-compatible · cost-optimization · proxy-server · litellm · provider-abstraction · routing-algorithms · rust · python · benchmarking · prometheus-metrics · claude-code · codex-cli | NVIDIA Switchyard is a Rust+Python LLM routing layer that picks the cheapest capable model per call while staying OpenAI/Anthropic API compatible. It works as a NeMo Relay plugin, a LiteLLM routing plugin, an embeddable library (switchyard-libsy), or a standalone proxy that Claude Code and Codex CLI can point at. | View Project → |
| harbor | ★ 3.2K | AI Tools | Python | llm-stack · docker-compose · local-llm · self-hosted · cli · orchestration · inference · open-webui · ollama · llamacpp · vllm · mcp · llm-ops · homelab · agents | Harbor is a CLI and companion app that boots a fully pre-wired local LLM stack via Docker Compose. One command starts backends (Ollama, llama.cpp, vLLM, MLX), frontends (Open WebUI, LibreChat), and services like SearXNG, Speaches, and ComfyUI, with cross-service config handled for you. | View Project → |
| OGAM | ★ 3.1K | AI Tools | TypeScript | offline-ai · on-device · gguf · llama.cpp · whisper · stable-diffusion · mcp · rag · react-native · privacy-first · tool-calling · vision-language-model · android · ios · macos · local-llm | Off Grid AI is a React Native app that runs GGUF LLMs, Whisper STT, Stable Diffusion image gen, vision models, and on-device RAG fully offline on Android, iOS, and Apple Silicon Macs, with MCP tool calling and local-network LLM server support. | View Project → |
| Bonsai-demo | ★ 3.1K | AI Tools | Shell | local LLM · small models · quantized models · ternary weights · 1-bit weights · vision-language · tool calling · MCP · offline inference · OpenAI-compatible API | Scripts and setup files for running Bonsai, Ternary-Bonsai, and Bonsai 2 models locally with llama.cpp or MLX. Includes Open WebUI integration, vision support, tool calling, and MCP connections. | View Project → |
| agent-scan | ★ 3.1K | AI Tools | Python | security · supply-chain-security · mcp · prompt-injection · agent-skills · scanner · cli · llm-security · ai-security · static-analysis · secrets-detection · tool-poisoning · vulnerability-scanning · python | Snyk Agent Scan is a Python CLI that discovers installed AI agent components (agents, MCP servers, and skills) on a machine and scans them for prompt injection, tool poisoning, malware payloads, and secret leakage. It auto-detects configs from Claude, Cursor, Copilot, Windsurf, Gemini CLI, and others. | View Project → |
| deepteam | ★ 3K | AI Tools | Python | red-teaming · llm-security · ai-safety · guardrails · jailbreak · prompt-injection · llm-evaluation · adversarial-attacks · vulnerability-scanning · ai-agents · penetration-testing · bias-detection · multi-turn · python · llm-testing · responsible-ai | DeepTeam is an open-source Python framework for red teaming LLM apps and AI agents. It ships 50+ vulnerability checks and 20+ adversarial attack methods, runs locally on top of DeepEval, and adds optional guardrails for production use. | View Project → |
| treg | ★ 2.9K | AI Tools | Python | agent tools · tool registry · MCP · API proxy · credential injection · CLI · skills · team sharing · tool catalog · self-hosted | Treg is a self-hostable registry and proxy for agent tools, with a searchable catalog of third-party endpoints, team APIs, CLIs, and skills. It injects credentials server-side and exposes tools through a CLI and MCP endpoints. | View Project → |
| xianyu-auto-reply-fix | ★ 2.7K | AI Tools | Python | auto-reply · customer-service · automation · xianyu · goofish · playwright · fastapi · websocket · multi-account · auto-delivery · chatbot · docker · llm-integration · e-commerce | Xianyu/Goofish smart customer-service system: FastAPI + SQLite + Playwright backend that drives AI auto-replies, keyword rules and auto-delivery across multiple marketplace accounts, with a full web admin console and Docker deployment. | View Project → |
| docmd | ★ 2.5K | AI Tools | TypeScript | documentation · static-site-generator · mcp · llms-txt · ai-context · rag · semantic-search · markdown · typescript · seo · i18n · versioning · openapi · plugins · docker · pwa | Docs compiler that turns one Markdown source into a static site plus machine-readable outputs: llms.txt, Open Knowledge Format bundles, an MCP server for agents, and a RAG AI assistant. TypeScript CLI, MIT licensed, installable via npx or Docker. | View Project → |
| DataDesigner | ★ 2.3K | AI Tools | Python | synthetic-data · data-generation · data-augmentation · llm · multimodal · mcp · tool-use · validators · seed-data · llm-judge · plugins · nvidia-nemo · person-sampling · python | NVIDIA NeMo Data Designer is a Python framework for generating and augmenting synthetic datasets with LLM, sampler, and image columns. It supports multimodal seeds, MCP tool-use traces, validators/LLM judges, plugins, and scalable resumable runs. | View Project → |
| wordpecker-app | ★ 2.3K | AI Tools | TypeScript | language-learning · vocabulary · llm · voice-agent · openai · image-generation · text-to-speech · quiz-generation · spaced-repetition · mongodb · react · typescript · docker · education · personalization | LLM-powered language-learning web app: curate vocabulary from books or videos, then practice via 5 generated quiz types, reading passages, image-based word discovery, and an OpenAI voice tutor that can edit your lists. React/Vite frontend, Node backend, MongoDB, Docker. | View Project → |
| OpenChatCut | ★ 2K | AI Tools | TypeScript | video-editing · mcp · agent-skills · local-first · multitrack-timeline · electron · remotion · text-based-editing · ffmpeg · transcription · webgl · captions · desktop-app · react · typescript · ai-generation | OpenChatCut is an AGPL local-first AI video editor: a built-in chat agent and external MCP agents (Claude Code, Codex) edit real, still-editable multitrack timelines with transcript cuts, captions, effects, generation and Remotion/FFmpeg exports. | View Project → |
| PageLM | ★ 2K | AI Tools | TypeScript | education · study assistant · document chat · RAG · quizzes · flashcards · AI podcasts · speech-to-text · text-to-speech · Ollama | PageLM is a self-hosted AI study platform that turns documents and other learning materials into chat, notes, quizzes, flashcards, and podcasts. It supports multiple hosted LLM providers and local Ollama models, with configurable embedding and speech services. | View Project → |
| snippai | ★ 1.9K | AI Tools | TypeScript | screenshot · OCR · image-analysis · LaTeX · markdown · translation · Electron · React · TypeScript · transformers.js · desktop-app · formula-recognition · table-extraction · code-understanding · color-detection · AI-tool | Snippai is an Electron desktop tool that uses AI (Transformers.js) to analyze screenshots: OCR text extraction, formula to LaTeX, table to Markdown, image description, code explanation, color detection, and translation. | View Project → |
| ai | ★ 1.8K | AI Tools | TypeScript | stripe · payments · billing · usage-based-billing · mcp · agent-skills · llm · ai-sdk · token-meter · oauth · plugins · claude-code · cursor · codex · typescript · python | Stripe's official AI toolkit: @stripe/ai-sdk and @stripe/token-meter for metering LLM usage into Stripe billing, a remote Stripe MCP server with OAuth, and installable agent skills/plugins for Claude Code, Codex, Cursor, and Grok. | View Project → |
| WFGY | ★ 1.8K | AI Tools | Jupyter Notebook | AI reasoning · RAG debugging · agent workflows · hallucination analysis · evaluation · knowledge graphs · retrieval · verification · protocols · troubleshooting | WFGY provides protocols and troubleshooting guides for AI reasoning, RAG, and agent workflows. Its public materials include a Problem Map for diagnosing failures, evaluation and verification resources, and a portable Goal Compiler for structuring human-AI tasks. | View Project → |
| lmstudio-js | ★ 1.8K | AI Tools | TypeScript | typescript · sdk · local-llm · llm-inference · embeddings · tool-calling · agents · nodejs · browser · model-management · streaming · structured-output | Official LM Studio TypeScript SDK for driving local LLMs: chat and text completion, embeddings, function/tool calling, autonomous agents, plus model load/unload and parameter control. Runs in Node and the browser, aimed at developers using local models instead of a cloud API. | View Project → |
| Risuai | ★ 1.7K | AI Tools | TypeScript | LLM chat · roleplay · AI characters · chatbot · group chat · lorebook · long-term memory · text-to-speech · plugins · cross-platform | Cross-platform LLM chat app for roleplay and storytelling. Supports multiple model providers, custom characters, group chats, lorebooks, long-term memory, plugins, and chat media. | View Project → |
| ml-mobileclip | ★ 1.7K | AI Tools | Python | vision-language · image-text models · CLIP · zero-shot classification · mobile inference · multimodal learning · model training · model evaluation | Official Python implementation of Apple's MobileCLIP and MobileCLIP2 vision-language models, with pretrained checkpoints, inference, training, and evaluation code. Includes lightweight variants designed for fast image-text inference on mobile devices. | View Project → |
| oxideterm | ★ 1.6K | AI Tools | Rust | ssh-client · terminal · ai-assistant · mcp · rag · agent-skills · tool-calling · byok · local-first · rust · gpui · sftp · port-forwarding · remote-desktop · cli · plugins | Native Rust/GPUI SSH and remote-ops workspace with a BYOK AI assistant (OxideSens) that inspects live sessions and executes approved actions. Bundles SSH/Mosh/Telnet/RDP/VNC/SFTP, port forwarding, mini-IDE, MCP, RAG and agent skills with no Electron, telemetry or subscription. | View Project → |
| gemma-translator | ★ 1.5K | AI Tools | JavaScript | offline translation · voice translation · on-device AI · speech-to-text · text-to-speech · Raspberry Pi · kiosk | An offline voice-translation app for Raspberry Pi that transcribes speech with Moonshine, translates it using Gemma 4 E2B through LiteRT-LM, and speaks the result. Includes a small-screen web UI and kiosk deployment scripts. | View Project → |
| amical | ★ 1.5K | AI Tools | TypeScript | dictation · speech-to-text · whisper · asr · local-first · offline · privacy · ollama · transcription · voice · electron · mcp · productivity · self-hosted · context-aware · meeting-notes | Amical is a local-first AI dictation desktop app (Electron) using Whisper for offline speech-to-text and Ollama-hosted LLMs for context-aware formatting per active app. Includes voice notes, hotkey workflows, and planned MCP voice control. | View Project → |
| DEEIX-Chat | ★ 1.5K | AI Tools | Go | ai-chat · model-routing · mcp · rag · self-hosted · multimodal · enterprise · llm-gateway · chat-ui · billing · sso · openai-compatible · vector-search · ocr · audit-logs · golang | DEEIX Chat is a self-hosted Go + Next.js enterprise AI workspace that unifies multi-provider model routing, multimodal chat, file RAG, MCP tools, billing, identity and admin audit in one deployable stack. | View Project → |
| tavily-python | ★ 1.4K | AI Tools | Python | web-search · search-api · rag · content-extraction · web-crawling · site-mapping · research-api · python-sdk · async · llm-grounding · agents · web-scraping · grounding · developer-tool | Python SDK for the Tavily API: web search, URL extraction, crawling, site mapping, and cited research, with sync and async clients. Commonly used to ground LLM/agent answers and build RAG context in one line of code. | View Project → |
| generative-ai-use-cases | ★ 1.4K | AI Tools | TypeScript | generative AI · business applications · chat UI · RAG · AI agents · image generation · video generation · voice chat · MCP · AWS | A deployable AWS application showcasing business generative AI workflows, including chat, RAG, agents, media generation, and voice interaction. Built on Amazon Bedrock, it includes authentication and configuration options for adapting use cases to an organization. | View Project → |
| Tracely-ai | ★ 1.4K | AI Tools | Python | agent-observability · llm-evals · ci-cd · regression-testing · tracing · opentelemetry · llm-as-judge · failure-clustering · replay · alerts · monitoring · llmops · self-hosted · clickhouse · github-action · agents | Trace-native CI/CD for AI agents: ingests OTLP traces, grades runs with LLM judges, clusters failures, freezes bad runs into hermetic replayable regression cases, and blocks the PR that would ship them again at $0 replay cost. Self-hosted stack with MCP endpoint and alerts. | View Project → |
| jobsync | ★ 1.3K | AI Tools | TypeScript | job search · resume review · job matching · job discovery · AI assistant · MCP · self-hosted · Ollama | Self-hosted job-search manager with AI resume reviews, job matching, cover-letter drafting, and scheduled job discovery. Includes an MCP server for agents to add jobs and interview questions with user approval; supports local Ollama or cloud providers. | View Project → |
| tools | ★ 1.3K | AI Tools | Python | agents · agent-tools · multi-agent · mcp · memory · browser-automation · computer-use · function-calling · python · aws-bedrock · swarm · web-search · image-generation · opentelemetry · ollama · openai | Python tool library for Strands Agents that gives LLM agents ready-made capabilities: file/shell/Python execution, memory backends, web search and scraping, image/video/audio generation, browser and desktop control, MCP client, and multi-agent swarm/graph orchestration. Experimental and security-sensitive. | View Project → |
| openinference | ★ 1.2K | AI Tools | Python | observability · tracing · opentelemetry · llmops · instrumentation · telemetry · evals · monitoring · span-attributes · ai-observability · debugging · aiops · semantic-conventions · agent-tracing · multimodal · python | OpenInference is an OpenTelemetry-based spec plus Python/JS/Java instrumentation packages that trace LLM and agent calls. It emits standardized spans for models, tools, retrievals, and MCP, exportable to any OTel-compatible backend such as Arize Phoenix. | View Project → |
| openpets | ★ 1.2K | AI Tools | TypeScript | desktop-pet · mcp · plugin-sdk · electron · typescript · claude-code · opencode · coding-agents · local-first · agent-integrations · sandboxed-plugins · desktop-companion · reminders · cli · cross-platform · notifications | Electron desktop-companion platform where sandboxed JS/TS plugins and coding agents (Claude Code, OpenCode, Cursor) or a local MCP stdio server drive animated pet reactions, reminders, timers and HUDs. Agent hooks stay local and sanitize code, paths and secrets. | View Project → |
| doc7 | ★ 1.1K | AI Tools | Go | document AI · multimodal · document conversion · PDF · Office files · vision-language models · Markdown · local AI · CLI · MCP · Go SDK · HTTP API | A Go CLI, SDK, MCP server, and HTTP service that converts PDFs, Office files, scans, and images into AI-ready Markdown using an OpenAI-compatible multimodal model. Supports local endpoints such as Ollama and LM Studio. | View Project → |
| stride-gpt | ★ 1.1K | AI Tools | Python | threat-modeling · security · STRIDE · MITRE-ATT&CK · DREAD · attack-trees · OWASP-LLM-Top-10 · SARIF · data-flow-diagrams · agentic-AI-security · cli · litellm · drawio · streamlit · secops | AI-powered threat modeling CLI and Streamlit app that uses LLMs to generate STRIDE threat models, attack trees, DFDs and mitigations from app descriptions, codebases or architecture diagrams. Supports MITRE ATT&CK/ATLAS mapping, DREAD scoring, and SARIF/Markdown/HTML reports. | View Project → |
| finger-frame-effect-ai | ★ 1K | AI Tools | JavaScript | AI video generation · video-to-video · video editing · hand tracking · video compositing · Gemini | A browser app and Python CLI that restyle uploaded videos with Gemini, track a two-hand finger-frame gesture with MediaPipe, and composite the generated video inside that frame. Requires your own Gemini API key. | View Project → |
| AI-Bootcamp | ★ 945 | AI Tools | Jupyter Notebook | bootcamp · tutorials · jupyter-notebooks · llm · rag · ai-agents · langchain · langgraph · ollama · fine-tuning · prompt-engineering · llm-evaluation · dspy · crewai · local-llm · education | Curated Jupyter notebook bootcamp covering the full LLM engineering stack: ML/LLM foundations, Ollama local models, RAG, LangChain/LangGraph agents, CrewAI, DSPy, fine-tuning and quantization. Best as a hands-on learning path rather than a runnable tool. | View Project → |
| selfhost-ai | ★ 936 | AI Tools | Shell | self-hosted · docker-compose · installer · llm · local-llm · rag · ai-agents · workflow-automation · mcp · homelab · vector-database · vps-deployment · monitoring · https-caddy · llm-ops | One-command Docker Compose installer that deploys a self-hosted AI stack on Ubuntu: Ollama local LLMs, Open WebUI, n8n automation, Dify/Flowise/Letta agents, RAG engines, vector DBs, ComfyUI and Grafana monitoring behind Caddy with automatic HTTPS. | View Project → |
| aimock | ★ 933 | AI Tools | TypeScript | mocking · ai-testing · llm-testing · mcp · a2a · ag-ui · vector-db · record-replay · fixtures · sse · streaming · chaos-testing · vitest · jest · openai · drift-detection | aimock is a zero-dependency mock server that stands in for every service an AI app talks to: LLM APIs, image/audio/video, embeddings, MCP tools, A2A agents, AG-UI streams, vector DBs and search. Point SDKs at one local port for deterministic offline tests, plus record & replay, chaos injection and drift detection. | View Project → |
| awesome-evals | ★ 923 | AI Tools | — | AI agent evaluation · LLM evaluation · benchmarks · evals · research resources · evaluation playbook | An annotated collection of papers, articles, talks, tools, and benchmarks for building and evaluating AI agents. Includes a practical playbook with runnable examples for graders, trajectory evaluation, error analysis, and CI gating. | View Project → |
| pipelock | ★ 912 | AI Tools | Go | agent-security · ai-firewall · egress-proxy · mcp-security · prompt-injection · ssrf-protection · dlp · secret-exfiltration · audit-receipts · signed-evidence · a2a · websocket-inspection · llm-security · security-scanning · github-action · golang | Go-based AI agent firewall that proxies and inspects HTTP, MCP, A2A, and WebSocket traffic for secret exfiltration, prompt injection, and SSRF, then emits mediator-signed action receipts for offline verifiable audit. Ships GitHub Action, sandbox and cluster deployment options. | View Project → |
| geo-optimizer-skill | ★ 900 | AI Tools | Python | aeo · geo · ai-seo · llm-seo · ai-visibility · llms-txt · citation-tracking · schema-markup · cli · mcp-server · seo-audit · python · astro · ci-cd · monitoring | Open-source Answer Engine Optimization / GEO CLI toolkit that scores any site 0-100 on AI-search readiness, generates robots.txt, llms.txt and JSON-LD fixes, and checks whether ChatGPT, Perplexity, Gemini or Google AI Overviews cite your brand. Ships as Python library, MCP server, Astro integration and CI/CD gate. | View Project → |
| wx-cli | ★ 898 | AI Tools | Rust | wechat · macos · sqlcipher · cli · rust · agent-skill · sse · rest-api · local-first · privacy · chat-search · real-time-monitoring · sqlite · contacts · media-decryption · llm-memory | Rust CLI and local REST/SSE service that decrypts and queries the macOS WeChat database, exposing chat history, contacts, search and live message events to agents. Ships an Agent Skill for Claude Code, Codex and Cursor; keys stay local and SIP must be disabled. | View Project → |
| clipforge | ★ 872 | AI Tools | TypeScript | ai-video-generator · short-video · ecommerce · image-to-video · text-to-video · voiceover · tts · subtitles · ffmpeg · mcp-server · self-hosted · aigc · ugc · batch-generation · video-editing · nextjs | ClipForge is a self-hosted, AGPL Next.js/Electron app that turns a product image or one-line topic into platform-ready e-commerce short videos: AI script/hook writing, storyboard image generation, TTS voiceover, subtitles and FFmpeg compositing. Exposes the same local pipeline via web UI, CLI, and MCP server. | View Project → |
| AITreasureBox | ★ 868 | AI Tools | Ruby | awesome-list · curated-list · ai · llm · agents · mcp · ai-tools · prompts · tutorials · papers · deep-learning · machine-learning · trending · resources · ruby · auto-updated | Auto-updated curated directory of AI repositories, tools, websites, papers and tutorials, with GitHub star rankings refreshed every two hours via Ruby scripts. It is a resource list, not an AI library or runnable product. | View Project → |
| ship-safe | ★ 849 | AI Tools | JavaScript | ai-security · agent-security · llm-security · prompt-injection · mcp-security · sast · secrets-scanning · sarif · cli · devsecops · supply-chain-security · static-analysis · ci-cd-security · owasp · red-team · vulnerability-scanner | CLI security scanner for AI-written software. A deterministic engine flags issues across app code, agents, MCP configs, prompts, deps, CI/CD and secrets, then an investigation layer confirms or refutes each finding with cited evidence in JSON/SARIF. | View Project → |
| stashbase | ★ 826 | AI Tools | TypeScript | ai-agents · mcp-server · rag · semantic-search · local-first · electron · markdown · writing · document-search · ocr · pdf-extraction · claude-code · codex · embeddings · wiki · typescript | StashBase is a local-first desktop writing workspace that pairs Claude Code, Codex, or a built-in agent with your own files. It adds semantic search, local PDF/OCR extraction, and an MCP server so agents can read, search, and edit project docs in place. | View Project → |
| hoop | ★ 823 | AI Tools | Go | agent-security · guardrails · data-masking · pii-redaction · sidecar · proxy · policy-enforcement · postgres · mssql · sql-guardrails · runtime-security · access-control · session-analyzer · human-in-the-loop · audit · go | MIT sidecar that sits on the wire between agents and your databases or HTTP APIs: it redacts sensitive fields in responses, blocks destructive statements before they reach the resource, and flags risky operations via a session analyzer. Configured with one YAML file, no agent-side changes. | View Project → |
| ima2-gen | ★ 792 | AI Tools | TypeScript | image-generation · video-generation · local-first · visual-workflows · coding-agent · prompt-studio · node-editor · canvas-editing · CLI · MCP | A local image and video generation studio with a CLI, browser UI, and Mac app. Routes jobs to providers including OpenAI, Grok, Gemini, NovelAI, and ComfyUI; includes agent skills and reproducible workflows. | View Project → |
| ima2-gen | ★ 776 | AI Tools | TypeScript | image-generation · video-generation · local-first · multi-provider · node-editor · canvas-editing · cli · mcp · agent-skills · comfyui · storyboard · background-removal · vectorize · prompt-library · electron-desktop · sse-streaming | Local-first image and video generation studio plus CLI with multi-provider routing (OpenAI, Grok, Gemini, NovelAI, ComfyUI). Ships node/canvas editing, storyboard mode, and packaged skills so coding agents can generate assets. | View Project → |
| cartcut | ★ 756 | AI Tools | TypeScript | video-editor · ffmpeg · electron · mcp · agent-video-editing · whisper · auto-captions · motion-graphics · keyframe-animation · layer-based-editing · screen-recording · webgl · chromakey · typescript · lit · macos-app | CartCut is a cross-platform Electron/Lit video editor with layer-based editing, keyframe motion graphics, FFmpeg rendering, Whisper AI auto-captions, and an MCP endpoint so AI agents can script edits programmatically. | View Project → |
| agentacct | ★ 754 | AI Tools | Python | agent-observability · cost-tracking · token-usage · llmops · local-first · dashboard · tui · cli · claude-code · codex · opencode · mcp · privacy · analytics · developer-tools · agent-analytics | Local-first CLI, TUI and dashboard that reads your coding agents' (Claude Code, Codex, OpenCode, Hermes) session logs to produce per-task work receipts: tools used, files changed, tests run, tokens and estimated cost, with evidence tiers and confidence labels. No login, no cloud, no telemetry. | View Project → |
| capcut-cli | ★ 722 | AI Tools | JavaScript | capcut · jianying · video-editing · cli · subtitles · srt · agent-skills · claude-code-plugin · automation · ffmpeg · whisper · shorts · templates · zero-dependency · json · wasm | Unofficial zero-dependency CLI that reads and writes CapCut/JianYing draft JSON directly to edit projects: subtitles, timing, speed, templates, and long-form-to-shorts cuts. Ships an agent skill and Claude Code plugin so LLM agents can drive edits, with no API or server. | View Project → |
| StoryMaker | ★ 721 | AI Tools | Python | text-to-image · character-consistency · personalization · diffusion · SDXL · IP-Adapter · LoRA · image-generation · face-preservation · story-visualization · training-code · inference-pipeline · diffusers · python | StoryMaker is a diffusion personalization method and inference/training pipeline that keeps characters consistent across text-to-image generations, preserving faces, clothing, hairstyles and bodies. Built on SDXL with IP-Adapter, LoRA and InsightFace encoders. | View Project → |
| arcjet-js | ★ 684 | AI Tools | TypeScript | security · prompt-injection-detection · pii-redaction · rate-limiting · bot-protection · agent-security · llm-security · tool-authorization · mcp · waf · sdk · typescript · runtime-security · sensitive-data | Arcjet's JS/TS SDK adds runtime security to AI apps and agents: prompt-injection detection, tool-call authorization, PII redaction, bot protection, and rate limiting. Framework adapters (Next.js, Node, Bun, Deno, etc.) plus @arcjet/guard for MCP servers and background jobs. | View Project → |
| hol-guard | ★ 670 | AI Tools | Python | agent-security · mcp-security · ai-antivirus · prompt-injection · secrets-detection · supply-chain-security · runtime-security · devsecops · plugin-security · skill-security · cli · claude-code · cursor · codex · gemini-cli · sarif | Local-first runtime security for AI agents: hooks and MCP proxies that classify shell commands, file access, package installs and tool calls, then allow, block or request approval. Also ships plugin-scanner, a CLI/CI scanner for agent plugins, skills and MCP servers. | View Project → |
| cs-board | ★ 666 | AI Tools | Python | AI video generation · whiteboard animation · text-to-speech · voice cloning · image generation · Chinese · local-first · storyboarding · dynamic infographics · video rendering | A local AI video production workbench that turns Chinese scripts and reference audio into narrated whiteboard animations or dynamic infographics. It connects to text and image model APIs plus an IndexTTS service, then renders the finished video as MP4. | View Project → |
| OpenWiki | ★ 633 | AI Tools | Rust | AI knowledge management · personal wiki · clipboard capture · knowledge graph · AI insights · local-first · desktop app · macOS · Windows · MCP | A desktop app that turns selected clipboard captures and saved links into an AI-organized personal wiki. It supports knowledge-base Q&A, graph visualization, insight reports, and MCP integration, with data stored locally in SQLite. | View Project → |
| surf-cli | ★ 621 | AI Tools | TypeScript | browser-automation · chrome · cli · computer-use · agent-tools · cdp · devtools · mcp · network-capture · screenshots · accessibility-tree · multi-browser · tailscale · zero-config · typescript · ai-agents | Surf is a zero-config CLI that lets AI agents control Chrome and other browsers via Unix-socket commands, no MCP relay or API keys required. It offers page reading, screenshots, network capture, remote Tailscale access, and also ships an MCP server. | View Project → |
| spirula-studio | ★ 618 | AI Tools | C++ | 3d-gaussian-splatting · 3d-reconstruction · neural-rendering · structure-from-motion · mesh-generation · vulkan · cuda · gpu-acceleration · quantized-training · vram-optimization · computer-vision · 360-camera · image-masking · cpp · cross-platform · cli-and-gui | Self-contained 3D Gaussian Splatting trainer: photos/video to splat to textured mesh in one binary, with Vulkan (NVIDIA/AMD/Intel/Apple) and CUDA backends. Built-in SfM, SAM masking, 360/fisheye support, and quantized training for 10M Gaussians in 8GB VRAM. | View Project → |
| Lynkr | ★ 605 | AI Tools | JavaScript | LLM gateway · model routing · AI coding tools · prompt caching · semantic caching · token compression · self-hosted · MCP · cost optimization | Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, Codex, and other AI coding tools. Routes requests across local and cloud providers, with semantic caching, prompt compression, and MCP tool support. | View Project → |
| agent-console | ★ 593 | AI Tools | JavaScript | AI coding agents · observability · token usage · cost tracking · local-first · self-hosted · Claude Code · Codex · team dashboard · LLM FinOps | A local-first dashboard for monitoring Claude Code and Codex sessions across one or more machines. It tracks tokens, cache activity, models, and estimated costs, with an optional self-hosted team hub and Prometheus metrics. | View Project → |
| HermesOffice | ★ 589 | AI Tools | TypeScript | AI office suite · document editing · AI agents · DOCX · XLSX · PPTX · PDF · Markdown · local-first · Electron · BYOK · MCP | A cross-platform desktop office suite with AI document editing and context-aware agents for documents, spreadsheets, slides, and PDFs. Supports common Office formats, local PDF conversion, and user-provided model API keys. | View Project → |
| Codex-QQ-Skin | ★ 568 | AI Tools | JavaScript | Codex · ChatGPT desktop · UI customization · desktop app · themes · macOS · Windows · developer tool | A macOS and Windows utility that injects custom themes into the Codex/ChatGPT desktop app, with skin management, local token statistics, and an optional theme-generation skill. It uses local Chromium DevTools Protocol injection rather than modifying the official app bundle. | View Project → |
| cli | ★ 536 | AI Tools | TypeScript | cli · ai-agent · aliyun · bailian · dashscope · mcp-server · qwen · multimodal · text-to-image · text-to-video · speech-recognition · skills · workflow · llm-tools · fine-tuning · tool-calling | Official Aliyun Model Studio (Bailian/DashScope) CLI that exposes Qwen chat, image/video generation, speech, knowledge retrieval, fine-tuning and managed agents as structured tool calls for AI agents. Runs as an npm/curl install and ships MCP server and skill support. | View Project → |
| OrcaBonsai-27B-Uncensored | ★ 533 | AI Tools | Python | abliteration · uncensored-llm · runtime-ablation · refusal-direction · quantized-llm · ternary-weights · mlx · apple-silicon · gguf · lora · safety-evaluation · residual-stream · llm-inference · activation-steering | Runtime refusal-direction ablation for Ternary Bonsai 2 27B: applies y -= alpha*(y·r)r at 129 residual writer sites in MLX, leaving the ~1.72-bit quantized weights bit-identical and alpha/layer tunable at inference. | View Project → |
| token-tracker | ★ 522 | AI Tools | Python | token tracking · cost analysis · Claude Code · Codex · Kimi Code · CLI · statusline · usage reports · heatmap · session monitoring · local-first | A local Python CLI that tracks token usage and estimated costs from Claude Code, Codex, and Kimi Code session data. It provides terminal reports, heatmaps, quota monitoring, statuslines, and a live session sidebar. | View Project → |
| Nomi | ★ 522 | AI Tools | TypeScript | local-first · electron · ai-video · text-to-video · text-to-image · comfyui · mcp · storyboard · timeline-editor · video-editing · bring-your-own-key · offline · desktop-app · image-generation · agent-driven · react | Local-first Electron desktop workbench for AI video: script, storyboard, image/video generation via any provider or local ComfyUI, timeline editing, and MP4 export. Ships 23 MCP tools so Claude Code, Codex, or Cursor can drive the whole pipeline. | View Project → |
| agentregistry | ★ 494 | AI Tools | Go | mcp · registry · ai-agents · skills · prompts · go · kubernetes · cli · governance · artifact-registry · oci · helm · a2a · curation · deployment · web-ui | Open-source registry for MCP servers, AI agents, skills, and prompts, with a Go CLI (arctl), admin web UI, PostgreSQL backend, and Helm/Kubernetes deployment. It publishes, curates, and distributes artifacts and auto-configures AI clients. | View Project → |
| velorn | ★ 488 | AI Tools | JavaScript | AI video · video editing · generative workflows · MCP · timeline editor · local agents · ComfyUI · desktop app | Velorn is a cross-platform desktop video editor with generative workflows backed by ComfyUI and a local MCP server offering 100+ tools for agent-driven project review, timeline edits, generation, and export. | View Project → |
| free-router-proxy | ★ 477 | AI Tools | JavaScript | LLM gateway · model routing · OpenAI-compatible API · provider failover · free models · local proxy · quota tracking | A local OpenAI-compatible gateway that ranks free models across configurable providers and fails over when a provider is unavailable, rate-limited, or returns no results. Includes a web UI for provider configuration and usage monitoring. | View Project → |
| thoughtdag | ★ 475 | AI Tools | TypeScript | infinite-canvas · thought-graph · context-engineering · llm · mcp · local-first · knowledge-graph · react-flow · pkm · human-in-the-loop · dag · agentic-search · self-hosted · ollama · note-taking · session-search | Desktop/CLI app that turns LLM conversations into an editable thought graph where wires define the model's next context. Includes a read-only MCP server to search local Claude Code, Codex, DeepSeek Harness and Pi sessions. | View Project → |
| entroly | ★ 469 | AI Tools | Python | context-compression · token-optimization · context-engineering · mcp · ai-agents · llm-proxy · receipts · reversible-compression · local-first · claude-code · github-copilot · cursor · codex · hallucination-detection · developer-tools · llm-cost-optimization | Local-first Context Assurance layer that selects budgeted, query-relevant context for AI agents and compresses it reversibly. Every reduction ships an auditable receipt plus a handle to recover the exact original bytes. Integrates via MCP, proxy, SDK, or agent wrapper. | View Project → |
| MemoryAgentBench | ★ 459 | AI Tools | Python | agent-memory · benchmark · llm-agents · evaluation · multi-turn · long-context · rag · retrieval · test-time-learning · conflict-resolution · llm-as-judge · memory-systems · research · iclr-2026 | ICLR 2026 research benchmark for evaluating memory in LLM agents across four competencies: accurate retrieval, test-time learning, long-range understanding, and conflict resolution. Ships harnesses for long-context, RAG, and agentic memory methods (mem0, Zep, Letta, Cognee) plus LLM-as-judge scripts. | View Project → |
| MinusPod | ★ 458 | AI Tools | Python | podcasts · ad detection · audio transcription · LLM · Whisper · self-hosted · RSS feeds · sponsor detection · audio editing | Self-hosted podcast server that transcribes episodes with Whisper, uses an LLM to identify ad segments, and serves edited audio through RSS feeds. Supports Anthropic, Ollama, OpenRouter, and OpenAI-compatible providers. | View Project → |
| mdflux | ★ 426 | AI Tools | Python | document conversion · Markdown · OCR · RAG · local-first · offline · PDF · batch processing · token efficiency | A local-first desktop app that converts PDFs, Office files, scans, and other formats into structured Markdown for LLM and RAG workflows. Includes OCR, batch processing, and optional AI cleanup; conversions run offline. | View Project → |
| ollaya | ★ 425 | AI Tools | Rust | local inference · decision models · classification · zero-shot classification · NLI · model serving · LLM routing · calibration · MCP · ONNX · Ollama-compatible CLI | A Rust runtime and server for pulling and running decision models locally, including classifiers and NLI models. Provides an Ollama-style CLI, a TypeSafe-compatible API, and an MCP server for agent access. | View Project → |
| Interceptor | ★ 421 | AI Tools | TypeScript | computer-use · browser-automation · desktop-automation · iPhone-automation · MCP-server · CLI · workflow-recording · agent-skills | Interceptor gives AI agents browser, macOS, and physical iPhone automation through a CLI and MCP server. It supports structured UI inspection and actions, workflow recording, and verification using the user's existing browser sessions. | View Project → |
| Pulse | ★ 420 | AI Tools | Swift | macos · menu-bar · usage-monitor · rate-limits · quota-tracking · claude-code · codex · cursor · github-copilot · token-spend · swiftui · multi-account · notifications · raycast · tmux · sketchybar | Pulse is a macOS menu-bar/edge-docked monitor showing remaining quota, rate-limit windows and reset times for 20 AI coding services (Claude Code, Codex, Cursor, Copilot, Grok, Kimi and more) using your existing logins. It also offers optional local token-spend tracking and JSON output for tmux/sketchybar/Raycast. | View Project → |
| classifier-dev | ★ 419 | AI Tools | TypeScript | zero-shot-classification · text-classification · cloudflare-workers · mcp-server · cli · api · llm · edge · batch-inference · calibrated-confidence · multi-label · openapi · serverless · agent-feedback · durable-objects · no-api-key | Zero-shot text classifier served by a single Cloudflare Worker: plain HTTP GET, CLI (classifier-dev), and MCP server, no API key or account. Batches up to 1000 texts per request with calibrated probabilities, multi-label support, and an LLM fallback chain when the primary decision model is down. | View Project → |
| hermes-web-search-plus | ★ 417 | AI Tools | Python | web-search · web-extraction · source-grounding · ai-agents · mcp · searxng · research-agent · provider-routing · llm-tools · caching · python · search-api · tavily · exa · hermes-agent · privacy | Hermes Agent plugin adding web_search_plus and web_extract_plus tools that return real source links and cleaned page text across 15 search and 9 extraction providers, with fallback routing, caching, and an optional local key-free DonSeTch MCP provider. | View Project → |
| jev-search | ★ 408 | AI Tools | TypeScript | web-search · llm-ranking · query-understanding · relevance-scoring · search-ui · multi-engine · cloudflare-workers · pwa · streaming-ndjson · serverless · self-hostable · typescript · no-generated-answers · rate-limiting · kv-cache | Jev Search is a Cloudflare Workers web app that sends your query to TypeSafe's Jev model, which picks sources, time range and search terms, then ranks Search1API results with visible relevance scores. It streams results per engine as NDJSON and returns links and snippets only, no generated answers. | View Project → |
| ms-cookbook | ★ 404 | AI Tools | HTML | cookbook · tutorials · llm · fine-tuning · rag · ai-agents · mcp · model-evaluation · aigc · diffusion-models · quantization · modelscope · learning-resource · developer-guide · inference | ModelScope Cookbook is an open-source, hands-on book (34 chapters) for building real AI applications with open-source models: model selection, inference, fine-tuning, evaluation, RAG, Agents, MCP and AIGC, with runnable examples using ms-swift, EvalScope, DiffSynth and Ollama. | View Project → |
| camofox-browser | ★ 397 | AI Tools | JavaScript | browser-automation · anti-detection · stealth-browser · headless-browser · rest-api · web-scraping · mcp · camoufox · fingerprint-spoofing · playwright · express · typescript · cli · proxy · session-management · accessibility-snapshot | TypeScript REST API server wrapping the Camoufox stealth Firefox engine so AI agents can automate browsers without bot detection. Offers multi-session contexts, persistent profiles, proxy/geo presets, accessibility snapshots, a CLI, Docker deployment, and OpenClaw/MCP integration. | View Project → |
| agent-skills-hub | ★ 394 | AI Tools | TypeScript | agent-skills · MCP servers · AI agents · Claude Code · Codex · directory · GitHub sync · quality scoring · security grading · project discovery | AgentSkillsHub is a searchable directory of open-source agent skills, MCP servers, coding assistants, and related tools. It syncs GitHub projects regularly and provides quality scoring, security grading, trending lists, and side-by-side comparisons. | View Project → |
| agent-prism | ★ 392 | AI Tools | TypeScript | AI observability · agent traces · trace visualization · LLM monitoring · OpenTelemetry · React components · debugging · Langfuse | AgentPrism is a React component library for visualizing and inspecting AI agent traces. It converts OpenTelemetry and Langfuse data into hierarchical timelines with trace browsing, span details, token usage, and cost information. | View Project → |
| meridian | ★ 378 | AI Tools | Rust | AI · developer productivity · work journal · activity tracking · daily summaries · ticket drafting · local-first · screen activity · Jira · MCP | Meridian creates a local work journal from screen activity, generates daily summaries and standups, and drafts Jira worklog updates and tickets for review. AI analysis uses a connected provider. | View Project → |
| omni | ★ 372 | AI Tools | Rust | context-compression · token-optimization · cost-reduction · cli · rust · mcp · hooks · claude-code · cursor · memory · prompt-caching · context-engineering · developer-tools · agentic-ai | Rust CLI plus MCP server that hooks around an AI agent's tool calls to strip noisy output and replace already-seen bytes with retrievable handles. Every removed byte is archived in local SQLite and can be retrieved verbatim; original Apache-2.0 source included. | View Project → |
| DSH-X | ★ 367 | AI Tools | JavaScript | deepseek · launcher · windows · plugin-manager · version-manager · tray-app · nodejs · rust · inno-setup · local-web-ui · startup-booster · self-update · portable-runtime · dsh · chinese | Windows launcher/manager for DeepSeek Harness: pick an installed DSH version, start or stop the official dsh web UI in your browser, toggle plugins, and auto-disable ones that break startup. Ships portable Node/npm and a Rust tray binary; not an AI model itself, just tooling around DSH. | View Project → |
| geo-score | ★ 362 | AI Tools | Python | GEO · AI search visibility · site audit · CLI · GitHub Action · Claude Code skill · versioned rubric · structured data · AI crawlers · llms.txt | A dependency-free Python CLI, GitHub Action, and Claude Code skill for scoring how ready a website is to be cited by AI answer engines. Uses a public, versioned rubric to check crawler access, structured data, content citability, and related signals. | View Project → |
| awesome-ai-plugins | ★ 359 | AI Tools | Python | awesome-list · curated-list · catalog · ai-plugins · claude-code · codex · gemini-cli · grok · mcp · agent-skills · plugin-registry · discovery | An awesome-style catalog of AI plugins, skills, and MCP servers for assistants such as Claude Code, Codex, Gemini CLI, and Grok. It is a Markdown discovery index plus Python listing/validation scripts, not an AI tool, agent, or framework itself. | View Project → |
| awesome-jev | ★ 351 | AI Tools | — | awesome-list · Jev · TypeSafe AI · System One · AI ecosystem · SDKs · browser agents · computer use · evaluations · open source | A curated directory of Jev and TypeSafe System One SDKs, applications, agent tools, research, and community resources. Useful for finding integrations and examples across browser automation, computer use, and other AI workflows. | View Project → |
| rizzo-flow | ★ 347 | AI Tools | Python | local-llm · structured-output · logits · llama.cpp · typed-decisions · probability-calibration · classification · offline · gguf · quantization · fastapi · pydantic · inference · system-one · zero-generated-tokens · jev-compatible | Local-first implementation of the Jev programing model: an HTTP API and CLI that read only the answer-letter logits from a single forward pass, returning typed, probability-bearing decisions (boolean, choice, score, number) from a GGUF LLM via llama.cpp with zero generated tokens. | View Project → |
| talkio | ★ 337 | AI Tools | TypeScript | multi-model-chat · group-chat · local-first · desktop-app · tauri · mcp · multi-provider · personas · byok · sqlite · streaming · markdown-rendering · mobile · privacy-focused · llm-client · cross-platform | Talkio is a local-first Tauri 2 + React 19 desktop/mobile app that puts multiple AI models (GPT, Claude, Gemini, DeepSeek, Groq, Ollama) in one group chat with personas, MCP tool calling and workspace/Git tools. | View Project → |
| chatpassport | ★ 333 | AI Tools | TypeScript | conversation portability · browser extension · local-first · privacy · conversation export · conversation import · cross-platform | A local-first Chrome extension that transfers conversation context between ChatGPT, Claude, Gemini, and DeepSeek. It lets users preview, export, and import chats, then review a continuation draft before sending it themselves. | View Project → |
| claude-code-karma | ★ 328 | AI Tools | Python | claude-code · observability · dashboard · session-monitoring · analytics · hooks · mcp · skills · agents · plugins · cost-tracking · token-usage · local-first · fastapi · sveltekit · live-sessions | Local-first dashboard that reads ~/.claude/ JSONL data to visualize Claude Code sessions: timelines, tasks, files, subagents, skills, hooks, plugins, tools/MCP usage, and token/cost analytics, plus live session tracking via hooks. Read-only, no cloud or telemetry. | View Project → |