Explore

Nebula is a local-first AI security workbench where agents assist recon, note-taking, and vulnerability analysis while the operator controls scope, approvals, and isolated execution of pentest tools.

AI Agents | Python · pentesting · cybersecurity

HiKid is an Electron/React desktop app where kids talk to a fully local AI English pal. It chains SoX recording with VAD, a Qwen3-ASR speech server, kitten-tts synthesis, and an Ollama LLM via pi-agent-core for offline voice chat.

AI Agents | TypeScript · voice-agent · speech-recognition

Neuro SAN Studio is a Python playground and CLI for the Neuro SAN multi-agent framework: define agent networks declaratively in HOCON, auto-generate networks with an Agent Network Designer meta-agent, plug in coded tools, MCP/A2A/LangChain tools, and test or deploy via ns init.

AI Agents | Python · multi-agent · agent-networks

Local-first agent OS that splits a request into roles, staffs each with specialist agents from your machine, private cloud and public hub via A2A cards, then runs and verifies with receipts. Ships as a plugin/CLI for Claude Code, Codex, Cursor and Gemini and works with any model.

AI Agents | Python · multi-agent · orchestration

A Python CLI, REST API, and SDK for scanning MCP servers and tools. Combines YARA rules, LLM analysis, Cisco AI Defense, and package or malware checks to identify security findings.

MCP | Python · MCP security · security scanning

30 runnable Jupyter notebooks teaching agent memory for LLMs: conversation buffers, vector stores, knowledge graphs, episodic/semantic/working memory, plus Mem0, Letta, Zep, Graphiti and LoCoMo benchmarks. A hands-on reference for choosing and building memory in production agents.

AI Agents | Jupyter Notebook · agent-memory · llm-memory

A Rust web search, scraping, crawling, and extraction service with a Firecrawl-compatible API, CLI, and MCP server. It can run locally or self-hosted, or connect to its managed API.

MCP | Rust · MCP server · web scraping

Local Go binary plus MCP server that indexes the session files coding agents already write to disk into one shared memory, so a fix found in Codex comes back in Claude Code or Cursor. Keyword search, no LLM or embeddings, with secret redaction and hook-based recall.

MCP | Go · agent-memory · session-history

C#/.NET port of LangChain offering composable chains, prompt templates, document loaders, embeddings and vector stores for building LLM and RAG applications, closely mirroring the original Python abstractions.

AI Frameworks | C# · langchain · csharp

Ongrid is a self-hosted ops AI agent in Go that coordinates specialist SRE/network/compute sub-agents to investigate alerts, correlate metrics, logs and traces, and pinpoint root cause, then act from Slack, Telegram, Lark or DingTalk. Includes RAG knowledge search, MCP server registry, skills catalog and approval-gated

AI Agents | Go · aiops · devops

A collection of agent skills and Python CLI tools for collecting Chinese-platform content, transcribing media, and organizing sources as searchable Markdown. Includes optional semantic search and an MCP server for agents to query and read the knowledge base.

Skills | Python · agent-skills · knowledge-base

Portable Markdown agent skill that both writes copy (headlines, microcopy, subject lines, strategic blog posts) and strips AI writing tells using all 33 patterns from blader's Humanizer. No code or dependencies; runs in any LLM harness via skills CLI, Claude Code plugin, or pasting SKILL.md.

Skills | Python · copywriting · humanizer

AgentDock is a self-hosted Go MCP runtime that gives AI agents permission-bounded access to files, shells, Git, browsers and containers on local machines, VPS hosts and Docker. It exposes tools over MCP Streamable HTTP with OAuth/Bearer auth and supports multi-device orchestration and Skills.

MCP | Go · mcp-server · ai-agents

fastCRW is a Rust web scraper, crawler and search API that outputs markdown or structured JSON and ships an MCP server plus CLI and Python/Node SDKs. Drop-in Firecrawl-compatible endpoints, single small binary, self-host or managed cloud.

MCP | Rust · web-scraping · crawler

Obot is a Go-based AI governance platform that provides MCP and LLM gateways, an MCP/Skills registry, sandboxed hosting for MCP servers and agents, identity/RBAC, and correlated audit logs across clients, models, and devices.

MCP | Go · mcp-gateway · llm-gateway

Binance Skills Hub is an open marketplace of SKILL.md capability packs that let AI agents (Claude Code, OpenClaw, LangChain, CrewAI) search tokens, trade, track wallets and use DeFi via natural language.

Skills | Python · crypto · agent-skills

Arcade MCP is an open-source Python framework for building MCP servers and tools, with a decorator API covering tools, resources, prompts, sampling, and elicitation. It adds OAuth/secret-managed "authorized tool calling", an evals CLI, and one-command deploy.

MCP | Python · mcp-server · mcp-framework

A dual-entry Skill package and local MCP server that lets AI agents (Claude Code, Codex, Cursor, OpenClaw) drive SolidWorks/AutoCAD via Python COM automation: modeling, assemblies, drawings, exports, DFM, FEA and motion studies, with a capabilities.yaml gate marking verified vs pilot features.

Skills | Python · solidworks · cad

A TypeScript template for deploying knowledge-based agents as a web chat, GitHub bot, or Discord bot. It syncs sources into a sandboxed file system and uses grep, find, and cat for retrieval without embeddings or a vector database.

AI Agents | TypeScript · knowledge agent · file search

StackQL is a Go framework that transpiles SQL into cloud, SaaS and API calls, so you can query and provision resources across 40+ providers. It ships as an MCP server (stdio, npm, PyPI, Docker, .mcpb) for Claude, Cursor and VS Code, plus exec/shell/srv modes and a Postgres wire protocol endpoint.

MCP | Go · mcp-server · sql

A desktop app and CLI for running and managing coding-agent sessions across machines. It integrates existing agent CLIs in tmux, supports swarms and Git worktrees, and provides domain-specific harnesses with tools and live viewers.

AI Coding | Dart · coding agents · agent harness

A collection of Sentry-specific agent skills and subagents for engineering workflows, including code review, security checks, pull request iteration, and documentation. Installable as a Claude Code plugin or through compatible skills.sh agents.

Skills | Python · agent-skills · code-review

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.

AI Tools | JavaScript · AI video generation · video-to-video

Self-hostable workflow automation platform with AI agents as workflow steps. Agents can use connected tools, knowledge bases, guardrails, and MCP; workflows support durable execution, integrations, and human approvals.

AI Agents | Java · workflow automation · visual editor

README-only curated hub of free AI agent resources: GitHub repos, YouTube courses, docs, blogs and communities for learning agents and multi-agent systems. Contains no code or runnable project, only links.

AI Agents | awesome-list · curated-resources

A curated, ranked directory of 167 AI agent harnesses, frameworks, and techniques, with comparison guides, setup templates, and playbooks. Includes an MCP server and JSON/llms.txt data for agent-accessible harness recommendations.

AI Agents | Python · agent harnesses · coding agents

Autonomous AI penetration testing platform: 50+ specialist agents chain offensive testing across web, API, cloud, AD, Kubernetes, IoT firmware, CI/CD and LLM endpoints, returning real exploits as proof. Runs on local LLMs (Ollama/llama.cpp) with a Privacy Gateway that tokenizes IPs, hosts and credentials locally.

AI Agents | Python · pentesting · red-team

Installable Agent Skills pack giving any AI agent YouTube transcripts, video search, channel browsing and playlist extraction via the TranscriptAPI REST service — no yt-dlp, headless browser or Google API key. Free tier, MIT.

Skills | agent-skills · youtube

Python content reader that fetches and normalizes URLs from platforms including YouTube, X, WeChat, Telegram, RSS, and Bilibili. It can be used as an MCP server, CLI, library, or agent skill, with optional video and audio transcription.

MCP | Python · MCP server · content extraction

gentle-shell turns Pi into an opinionated coding-agent workspace: orchestrator plus focused subagents, ODD/SDD-OpenSpec workflows, strict TDD evidence, native change review, and skill discovery. Built for developers who want inspectable, human-led agent workflows in TypeScript.

AI Coding | TypeScript · ai-coding-agent · agent-harness

Microsoft's security-oriented MCP runtime that loads WebAssembly components from OCI registries and exposes them as sandboxed agent tools. Built on Wasmtime with capability-based permissions, so untrusted tools run isolated from the host. Early development, Rust, MIT.

MCP | Rust · mcp-server · wasm

Go TUI that acts as mission control for AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode). One terminal shows every session, with fork, groups, MCP/skill managers, git worktrees, cost tracking, and remote control via a conductor bot.

AI Coding | Go · tui · terminal

Enterprise MCP Gateway & Registry that puts all MCP servers, A2A agents, skills, and custom AI assets behind one OAuth-protected entry point. Adds semantic tool discovery, per-user egress auth, access scopes, and audit trails, deployable on EKS, ECS, or Docker Compose.

MCP | Python · mcp-gateway · mcp-registry

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.

AI Tools | Jupyter Notebook · bootcamp · tutorials

StackBlitz's Bolt Slides is a React deck engine plus a bundled agent skill: any coding agent composes slides as live React components, exporting a responsive web app deck instead of static slides.

Skills | TypeScript · presentations · slides

Google's SAM (Sovereign Agent Mesh) is a Go P2P networking layer that lets autonomous agents discover each other, authenticate zero-trust style, and invoke tools across an MCP/A2A mesh, with optional self-hosted control plane for data sovereignty.

AI Agents | Go · agent-mesh · p2p

Citra is a local-first MCP server (npx -y @sylphx/citra) that gives agents structured PDF text, tables, OCR, visual crops and page-level citations. Native Rust engine, three tools: read_pdf, search_pdf, pdf_evidence.

MCP | Rust · pdf · ocr

RepoPrompt CE is a free native macOS app that engineers reviewable context for AI coding agents from files, CodeMaps, repo structure and Git diffs, with a bundled MCP server and CLI so external agents can search repos and run agent sessions.

AI Coding | Swift · context-engineering · coding-agents

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.

AI Tools | Shell · self-hosted · docker-compose

Citra is a local-first MCP server (npx -y @sylphx/citra) that gives AI agents structured PDF reading: text, tables, OCR, visual crops, and page-level citations via read_pdf, search_pdf, and pdf_evidence. Native Rust engine, no API key, fails closed without the platform binary.

MCP | TypeScript · pdf · ocr

A local MCP server and CLI that converts documents into Markdown for AI agents. Its Rust PDF engine supports reading, search, comparison, and evidence extraction with page-level citations, table geometry, and optional OCR.

MCP | TypeScript · MCP server · document conversion

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.

AI Tools | TypeScript · mocking · ai-testing

mcpc is a universal CLI client for MCP, mapping every MCP operation (tools, prompts, resources, tasks, skills) to shell commands over stdio and Streamable HTTP. It keeps persistent sessions, supports OAuth 2.1, JSON mode for scripting, an MCP proxy for AI sandboxes, and experimental x402 payments.

MCP | TypeScript · mcp-client · cli

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.

AI Tools | AI agent evaluation · LLM evaluation

Citadel is a plugin operating layer for Claude Code and OpenAI Codex that adds a single /do entry point, repo-local persistent memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets in isolated worktrees, with evidence-based verification states (passed/failed/blocked/unknown).

AI Coding | JavaScript · claude-code · openai-codex

Official Ruby SDK for building MCP clients and servers. Supports stdio and Streamable HTTP transports, Rails integration, OAuth 2.1 authorization, and protocol features including tools, prompts, resources, notifications, and progress.

MCP | Ruby · SDK · client

A desktop and headless workstation for Codex CLI, Claude Code, and ACP-compatible agents. It combines agent sessions with task scheduling, Git worktree management, remote control, and MCP and skills marketplaces.

AI Coding | TypeScript · AI coding agents · agent workstation

CLM serves a contrastively trained model that scores candidate actions against a state, with an API for typed decisions and ranking. Use it for agent action selection, tool routing, or verifying and ranking generated solutions.

AI Frameworks | Python · contrastive learning · state-action scoring

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.

AI Tools | Go · agent-security · ai-firewall

Ix maps repositories into a persistent graph of symbols, calls, imports, and relationships. Its CLI and MCP server let developers and coding agents query architecture, trace flows, and assess change impact across sessions.

AI Coding | TypeScript · codebase-understanding · code-analysis

FastAPI + LangChain RAG service that embeds documents per file_id and stores them in PostgreSQL/pgvector (or Atlas MongoDB). It exposes async add/query/delete routes with JWT-verified owner scoping, built mainly as the retrieval backend for LibreChat.

RAG | Python · fastapi · langchain

FastAPI service that indexes documents with LangChain and stores embeddings in PostgreSQL/pgvector, exposing ID-based add/query/delete RAG endpoints. Built for LibreChat integration, with JWT-based per-user and entity ownership scoping on every read and delete.

RAG | Python · fastapi · pgvector

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.

AI Tools | Python · aeo · geo

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.

AI Tools | Rust · wechat · macos

A remote MCP server for the Cloudflare API. Its code-mode tools let agents search API schemas and execute requests while keeping the endpoint catalog on the server to reduce context usage.

MCP | TypeScript · Cloudflare API · MCP server

Local MCP server plus Figma plugin that gives coding agents two-way access to the canvas: read a selection into framework-aware code, or write frames, text, auto-layout, styles, variables and components back into Figma. 113 tools, works with Claude Code, Cursor, Codex or any MCP client on the free Figma tier.

MCP | TypeScript · figma · mcp-server

Self-hostable TypeScript engine plus Next.js app for AI-native document workflows: OCR ingestion, pgvector hybrid RAG, knowledge graph, LLM abstractions, and Inngest background jobs. Ships a startup-accelerator reference app with role-based access and missing-document detection.

RAG | TypeScript · pgvector · knowledge-graph

An agent skill and Node.js CLI that detects an app's production needs, plans infrastructure changes for approval, applies them using your provider accounts, and verifies results. Supports tested workflows for hosting, databases, domains, email, payments, and Supabase auth.

Skills | TypeScript · agent-skill · deployment

MCP server that exposes Unreal Engine 5 editing to AI assistants through a native C++ Automation Bridge plugin. Covers assets, actors, levels, Blueprints, Sequencer, Niagara and console commands via HTTP/SSE or a TypeScript WebSocket bridge.

MCP | TypeScript · mcp-server · unreal-engine

CUGA is a Python agent harness for enterprise tasks across web interfaces and APIs. It supports MCP and OpenAPI tools, multi-agent workflows, policy controls, human approvals, agent skills, and document RAG.

AI Agents | Python · enterprise-agent · computer-use

Official Python SDK for LM Studio: connect to a local LM Studio server to run chat, completion, tool-use, and schema-constrained inference with locally hosted LLMs, with sync and async clients plus model load/unload management.

AI Frameworks | Python · python-sdk · llm

Python framework for declaring and running typed, composable AI methods in .mthds files. It orchestrates multi-step LLM pipelines, model routing, document extraction, and structured outputs.

AI Frameworks | Python · AI workflows · DSL

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.

AI Tools | TypeScript · ai-video-generator · short-video

Community-curated directory and hosted registry for Model Context Protocol servers, indexing ~7,700 entries as structured metadata. Provides a free search API, normalized server profiles, install-config previews for Claude Desktop/Cursor/Codex/VS Code, and a registry MCP server.

MCP | TypeScript · mcp-servers · model-context-protocol

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.

AI Tools | Ruby · awesome-list · curated-list

Official Jina AI remote MCP server exposing Reader, Search, Embeddings and Reranker APIs as MCP tools (read_url, search_web, search_arxiv, sort_by_relevance, extract_pdf). Runs on Cloudflare Workers with Streamable HTTP, supports include/exclude tool filtering, and plugs into Claude Code, Cursor, LM Studio and Codex.

MCP | TypeScript · mcp-server · remote-mcp

DSCODE is a macOS terminal coding agent harness built on DeepSeek Harness: a persistent shell writes code and runs tests, and sessions see each other so agents can hand off tasks, review diffs and share memory. Ships a TUI, CLI, Chrome MCP, subagents and independent auto-review.

AI Coding | JavaScript · coding-agent · terminal

FinanceMCP is a TypeScript MCP server exposing 19 financial data tools over stdio and Streamable HTTP. It routes queries across Tushare, Qveris, Twingly and Binance with automatic fallback, covering stocks, funds, bonds, macro indicators, news and crypto, with source attribution on every result.

MCP | TypeScript · mcp-server · finance

VT Code is a Rust terminal coding agent: one static binary with a keyboard-first TUI, headless exec, sandboxed tool execution, durable sessions, built-in evals, and MCP, Agent Skills, Plugin, and ACP extensibility across OpenAI, Anthropic, Gemini, and local models.

AI Coding | Rust · terminal · tui

Agent-driven video editing skill installed into Claude Code, Codex, or Gemini CLI: it transcribes with word timings, styles captions and motion graphics in HTML/CSS, and renders MP4s through VEED's renderer via a local CLI.

Skills | TypeScript · agent-skill · video-editing

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.

AI Tools | JavaScript · ai-security · agent-security

Obsidian desktop plugin that scans, browses, creates, and edits agent skills, commands, rules, and agent files across 17 coding tools like Claude Code, Cursor, and Codex. Includes a skills.sh marketplace installer and optional local usage analytics via skillkit.

Skills | TypeScript · agent-skills · obsidian-plugin

A local-first MCP server and CLI that records project issues, attempts, fixes, and decisions for coding agents. It provides persistent context across sessions and warns agents before they repeat failed approaches.

MCP | Python · coding-agent-memory · MCP-server

Rust MCP server exposing headless IDA Pro (idalib 9.4) to AI agents for disassembly, decompilation, xrefs, and binary loading. Supports stdio and HTTP transports, multi-database workspaces, and an opt-in debugger; requires a licensed IDA Pro install.

MCP | Rust · mcp-server · reverse-engineering

A PostgreSQL server and extension that automate embedding generation and upkeep, with APIs and SQL functions for semantic, full-text, and hybrid search. Use it to build RAG retrieval on PostgreSQL, including managed databases that cannot install extensions.

RAG | Rust · PostgreSQL · vector search

An MCP server and SDK that let coding agents drive a running web or desktop app and verify behavior using DOM, network, console, and application-state evidence. Returns pass, fail, or unknown verdicts with source locations when available.

MCP | TypeScript · MCP server · agent testing

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.

AI Tools | TypeScript · ai-agents · mcp-server

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.

AI Tools | Go · agent-security · guardrails

Memorix is a local-first cross-agent memory layer, shipped as an MCP server plus CLI/SDK, that gives coding agents shared project memory: observations, Git-derived facts, reasoning, code state, knowledge pages and orchestration. SQLite is canonical with optional Orama/LanceDB retrieval.

MCP | TypeScript · mcp-server · agent-memory

macOS computer-use agent loop that OCRs the screen and the accessibility tree, then asks a TypeSafe classifier for one action per step (~$0.0002, sub-second); a writer LLM is only called for free text. Cheap alternative to screenshot-based frontier-model agents.

AI Agents | Python · computer-use · gui-automation

Single-file local memory store for AI agents: hybrid FTS5 + CoreML vector search over text, images, and video in one .wax file. Ships as an MCP server (waxmcp) and Swift SDK so Claude Code, Codex, Cursor, and Apple Foundation Models share the same on-device memory, with no server or cloud.

MCP | Swift · memory · rag

BOSS is an Apache-2.0 Kotlin/Compose Multiplatform desktop harness that runs Claude Code, Codex, Gemini or OpenCode with an embedded browser, terminal, editor, secrets and 100+ MCP tools. It exposes the app itself to agents via mcp__boss__* tools, with per-tool RBAC, kill-switches and runtime plugin hot-reload.

AI Agents | Kotlin · agent-harness · mcp

Self-hosted AI memory layer running as a Cloudflare Worker (D1, Vectorize, Workers AI) that exposes MCP memory tools — remember, recall, append, link, share — so Claude, ChatGPT, Cursor and other MCP clients share one persistent, semantically searchable second brain.

MCP | TypeScript · mcp-server · ai-memory

A self-hosted MCP server that gives AI agents and operators shared Playwright browser sessions. Includes human takeover, reusable auth profiles, approval gates, audit trails, and HTTP, stdio, and REST interfaces.

MCP | Python · browser automation · human-in-the-loop

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.

AI Tools | TypeScript · image-generation · video-generation

Evidence-backed collection of use cases, patterns, prompts, and starter code for TypeSafe Jev, a System One model that returns typed Choice/Score/Noul answers with probabilities and confidence for classification, routing, scoring, and guardrails. Includes Python and TypeScript quickstarts.

Skills | Python · awesome-list · prompt-patterns

A Rust framework for building LLM agents, typed task graphs, and streaming RAG pipelines. It includes indexing and query components, tool and MCP integrations, and connectors for LLM providers and vector stores.

AI Frameworks | Rust · LLM agents · RAG

Official LINE MCP server exposing Messaging API tools so AI agents like Claude Desktop or Cline can push/broadcast messages, manage rich menus, look up user profiles and follower IDs, and check message quota. Runs via npx or Docker with a channel access token.

MCP | TypeScript · mcp-server · line

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.

AI Tools | TypeScript · image-generation · video-generation

Multi-agent AI stock analysis and trading system: 13+ specialized agents (MCP-based) detect surge stocks, produce analyst-grade PDF reports, and run simulated or live trades for KRX and US markets via Telegram alerts.

AI Agents | Python · multi-agent · stock-analysis

Biologically-inspired long-term memory layer for AI agents: memories decay by default and strengthen on retrieval, with buffer/episodic/semantic consolidation. SQLite-backed, zero runtime deps, exposes MCP so Claude Code, Cursor, Codex and other agents share one portable store.

AI Agents | TypeScript · agent-memory · long-term-memory

Aeon is an autonomous agent framework that runs unattended on GitHub Actions. Skills are plain SKILL.md prompts scheduled on cron that ship PRs, disclose vulnerabilities, deploy apps, and repair themselves, driven by Claude Code, Grok, Codex and other harnesses.

AI Agents | Shell · autonomous-agents · agent-framework

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.

AI Tools | TypeScript · video-editor · ffmpeg

Storybloq gives Claude Code and Codex a Git-backed project memory and workflow system, storing stories, plans, lessons, and handovers in a `.story/` directory. It includes a CLI, MCP server, agent skills, and an optional Mac app.

AI Coding | TypeScript · Claude Code · Codex

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.

AI Tools | Python · agent-observability · cost-tracking

Bun/TypeScript LangGraph agent for nutrition advice. Combines chat, YOLO food-image analysis, and version-aware RAG over official dietary guidelines, with agent skills/tools, an Express API, and Docker deployment.

AI Agents | TypeScript · rag · langgraph

Open source AI dev agent for Unity that writes C#, edits scenes and assets, and hot-reloads changes without domain reload while preserving Play Mode. Built in Rust/Tauri with Vue frontend, Roslyn semantic analysis, runtime debugging and visual version control for YAML assets.

AI Coding | Rust · unity · gamedev

Local-first Rust MCP server and CLI that indexes a repository and serves symbol search, semantic code search, call graphs, dependency impact analysis, and doc RAG to coding agents like Claude Code, Cursor, and Codex.

MCP | Rust · mcp-server · code-intelligence

A pair of markdown skills for coding agents that enforce spec approval, test-driven implementation, risk-based verification, and evidence reports. Includes a companion HTTP/JSON API review skill and a rate-limiter demo.

Skills | Python · agent-skill · coding-agents

GoRaven is a self-hosted, team-oriented AI agent platform in Go that gives each user an isolated agent workspace with tool calling, code/shell execution, MCP integration, RAG knowledge, and an installable skill marketplace. One Docker command runs it with OpenAI, Claude, DeepSeek, Qwen, or Ollama backends.

AI Agents | Go · ai-agent · multi-agent