Explore

A local-first TypeScript CLI for coordinating human and AI-agent work in Git repositories. It tracks tasks, decisions, sessions, evidence, and handoffs, and supports supervised teams and deterministic multi-agent workflows.

AI Agents | TypeScript · multi-agent coordination · agent harness

quackd is a Python CLI that connects multiple robots (Microduck, Open Duck Mini, LeRobot arms, AlohaMini, ToddlerBot, ROS bases) and pilots each with an LLM agent. It enforces .duck safety contracts, supports flocks, MCP, simulation and local models.

AI Agents | Python · robotics · embodied-ai

Rust LLM router and gateway that sits in front of any agent harness: routes each model call, MCP tool/skill, and ACP sub-agent to the cheapest adequate path, with OTel telemetry and a git-owned policy-lock it improves from admitted eval evidence. Reports ~33% cost cut on Terminal-Bench 2.1 at near-parity accuracy.

AI Tools | Rust · llm-router · model-routing

Microsoft's agent skills pack that teaches AI coding agents to drive the Dataverse MCP server, Dataverse CLI, Python SDK and PAC CLI for modeling, querying, deploying and administering Power Platform / Dynamics 365 environments via natural language.

Skills | agent-skills · dataverse

Python MCP server exposing Chinese stock market data (historical/realtime quotes, news, financial statements, insider trades, technical indicators) as tools via akshare-one, with per-domain source fallback between eastmoney, sina and xueqiu. Runs in stdio or streamable-HTTP mode.

MCP | Python · mcp-server · stock-data

Self-hosted C# MCP server exposing 62 tools of SEC filings, XBRL financials, 13F, insider/congressional trades, short data, FRED, CFTC/CBOE and daily prices so AI agents can query market data directly. Cloud adds transcripts, live quotes, options Greeks and a screener.

MCP | C# · mcp-server · financial-data

An open set of agent skills, plugins, and templates for running a one-person company with Claude Code or Codex. It provides workflows for weekly planning and retrospectives, task management, and department-specific context.

Skills | HTML · agent-skills · Claude Code

A Python red-team and C2 framework with an MCP server exposing 153 tools to AI clients, plus autonomous and multi-agent workflows. Its main purpose is security testing rather than general-purpose AI development.

MCP | Python · MCP server · AI agents

Self-hosted AI studio bundling local video/image/music/voice generation, LoRA training, hybrid RAG, desktop screen agents and up to 20 parallel coding agents in git worktrees on one GPU, driven from a Studio UI or via MCP and agent skills from Claude Code, Cursor or Codex.

AI Agents | Python · self-hosted · local-ai

Self-hosted Telegram AI assistant that files voice notes, photos and messages into an Obsidian-compatible markdown vault with layered memory (daily logs rolled up into CORE.md cards). Supports MCP servers, skill files, five LLM providers and Google Workspace actions. One-command install on a VPS.

AI Agents | TypeScript · telegram-bot · long-term-memory

Memex is a local-first Rust CLI that indexes coding-agent transcripts (Claude Code, Codex, Cursor, OpenCode, Copilot, Pi) and searches them with BM25 plus optional embeddings for hybrid retrieval. It exposes the index through a TUI/web/native apps, an MCP server, and an installable agent skill, and can resume sessions,

RAG | Rust · claude-code · codex

A Claude/agent skill that turns a brief into scored ad concepts using 20+ structured ideation methods and a 571-case award-winning campaign library for empirical originality checks and Cannes-calibrated evaluation loops.

Skills | Python · agent-skill · claude-skill

Apache-2.0 MCP server giving an AI live control of an open Altium Designer session (plus KiCad/EasyEDA Pro backends) through a DelphiScript bridge. Exposes ~400 tools for schematic, PCB, library, design-review, audit, placement and autonomous design-plan execution.

MCP | Python · altium · kicad

Lobu is a self-hosted, event-sourced context layer for AI agents: it ingests connectors, webhooks and conversations into an append-only log linked to typed entities. Any MCP client (Claude, Codex, ChatGPT) reads and writes the same permission-aware memory, and persistent specialist agents can own durable responsibiliti

AI Agents | TypeScript · agent-memory · multi-agent

MCP server that gives AI agents eyes and hands on a real iPhone through macOS iPhone Mirroring: screenshot, tap, swipe, and type with 38 tools. It does OCR plus YOLO icon detection to expose tap coordinates, and can generate replayable SKILL.md flows from app exploration.

MCP | Swift · mcp-server · ios-automation

Go-based runtime for Anthropic's Agent Skills standard: write a SKILL.md, compile it into a portable agent, and run it in Docker, Kubernetes, air-gapped, CI, or as an A2A endpoint. Adds egress allowlists, encrypted secrets, NDJSON audit logs, MCP client, Slack/Telegram channels, and multi-provider LLM fallback.

AI Agents | Go · agent-runtime · agent-skills

Toolport is a local-first MCP gateway that connects your MCP servers once and shares them with Claude, Cursor, Codex, VS Code and other clients. It adds lazy tool discovery for large token savings, tool integrity/quarantine, OS-keychain secrets, and per-client profiles with call approval.

MCP | Rust · mcp-gateway · mcp-server

MAGDA is a C++20 digital audio workstation with an integrated AI chat and agent system. Natural-language requests generate and execute DAW commands through a custom DSL; it also supports local inference and documents a remote MCP API.

AI Agents | C++ · AI music production · DAW

An open-source MCP integration platform for connecting AI applications to APIs, data sources, and tools. Includes SDKs, an MCP server catalog, an explorer, and session monitoring; can be self-hosted.

MCP | TypeScript · integration platform · agentic AI

Official Python MCP server for Opik, Comet's open-source LLM observability and evaluation platform. Exposes read/list/write tools so MCP hosts like Claude Code, Cursor and VS Code can query traces, log scores, manage datasets and save prompt versions.

MCP | Python · mcp-server · llm-observability

Self-hosted MCP server exposing 129 tools for Google Drive, Docs, Sheets, Slides, and Calendar, with local OAuth, multi-account, service-account, and team-mode HTTP auth. Works with Claude Desktop, Gemini CLI, and other MCP clients over stdio or Streamable HTTP.

MCP | TypeScript · mcp-server · google-drive

LambChat is a full-stack platform for deploying and managing governed AI agents. It includes a DeepAgents/LangGraph runtime, MCP integrations, skills and memory, human approvals, scheduled tasks, sandbox execution, and web, mobile, and desktop clients.

AI Agents | Python · multi-agent · agent runtime

Go MCP server that indexes a codebase into a knowledge graph (SQLite by default, optional Postgres/pgvector) and exposes 3 tools / 30 actions so AI coding agents get targeted subgraphs instead of grep-and-read context, cutting tokens ~65% and tool calls ~85%.

MCP | Go · mcp-server · knowledge-graph

OMEGA is a local-first persistent memory system for AI agents, exposed as an MCP server and Python library. It stores memories in SQLite and uses on-device embeddings for semantic recall across coding sessions and supported clients.

MCP | Python · persistent memory · AI agents

MCP server that gives AI agents persistent long-term memory: it stores memories as OKF v0.2 markdown files plus a SQLite FTS5 index, exposing six tools for store, retrieve, search, delete, and session checkpoints, with per-project namespaces.

MCP | Python · mcp-server · agent-memory

Open measurement and conformance layer for AI-agent telemetry. Audits token and usage accounting with PASS/FAIL/UNPROVABLE CI checks, reads Codex rollout logs locally to expose retries and duplicate records, and runs preregistered harness experiments.

AI Tools | Python · agent-observability · token-accounting

Browser-native framework for 3D AI agents: GLB/glTF avatars driven by LLM brains with memory and emotions, embedded anywhere as a web component. Ships MCP servers, x402/Solana/EVM autonomous payments, character studio, and an animation gallery.

AI Agents | JavaScript · 3d-agents · avatars

Node9 is a security proxy that sits between AI coding agents and their tools: it scans past sessions for leaks, blocks risky commands before execution, gates MCP servers, and produces audit reports. Works with Claude Code, Codex, Cursor and any MCP server.

AI Tools | TypeScript · agent-security · mcp-security

A model-agnostic Codex skill for planning editorial visuals and compiling image-generation prompts. It includes style presets, layout and material rules, model adapters, and workflows for evaluating and iterating on generated images.

Skills | image-generation · prompt-engineering

An agent skill that guides logo design from brief and research through concepting, SVG construction, testing, and delivery. Includes dependency-free tools for SVG audits, test sheets, presentation boards, and favicon exports, plus a searchable library of 1,400+ reference logos.

Skills | HTML · logo design · agent skill

Peri is a lightweight Rust coding agent (~50MB RAM) with a TUI, headless mode, ACP and MCP support. It runs Claude Code-style plugins, skills, workflows, parallel agents, web search, and Langfuse tracing on top of Anthropic or OpenAI-compatible endpoints.

AI Coding | Rust · coding-agent · tui

Agent-first design workspace where humans and LLM agents co-edit web layouts, slides, wireframes, 3D scenes, and motion videos on one versioned document. Exposes MCP/WebMCP, a dsa CLI and an agent skill, with BYOK media generation and multi-format export.

AI Tools | TypeScript · agent-first · design-workspace

Python RAG demo that indexes documents into Chroma, answers questions via LangChain models, and lets you visually explore question/snippet embeddings with Renumics Spotlight and UMAP to debug and evaluate retrieval quality.

RAG | Python · langchain · streamlit

An MCP server that lets AI clients plan, validate, generate, and deploy Cisco Packet Tracer networks from natural-language requests. Includes tools for routing, DHCP, VLANs, live device inspection, connectivity checks, and configuration security audits.

MCP | Python · Cisco Packet Tracer · network automation

Procoder is a single Go binary that gives AI coding agents a non-negotiable commit gate, refusing quality controllers for spec/plan/test/release steps, and a lessons loop that closes escaped bug classes. No runtime deps; adapters for 20+ agents.

AI Coding | Go · code-quality · commit-gate

Remnic provides local-first, Markdown-backed memory for AI agents, with hybrid search, provenance, correction and retrieval-quality controls. Agents access the shared store through MCP or HTTP integrations.

RAG | TypeScript · agent memory · long-term memory

Electron desktop GUI for the Pi and oh-my-pi coding agents, combining streaming chat, file tree, CodeMirror editor, terminal, and a diff-review rail with commit/push/PR actions. Adds permission rules, multi-workspace sessions, and optional Claude/Codex council planning. Alpha.

AI Coding | TypeScript · coding-agent · desktop-gui

A Go, cloud-native gateway that unifies many LLM providers (OpenAI, Anthropic, Groq, Ollama, DeepSeek, and more) behind one OpenAI-compatible API. Adds MCP tool discovery, streaming, vision, OIDC auth, and OpenTelemetry/Prometheus metrics for self-hosted LLM traffic.

AI Tools | Go · llm-gateway · proxy

CLI-JAW is a local personal AI assistant that coordinates coding-agent CLIs including Claude, Codex, Cursor, Copilot, and OpenCode. It provides shared memory, session management, and terminal, web, desktop, and messaging interfaces.

AI Agents | TypeScript · AI assistant · multi-agent

A Claude Code skill for creating deterministic, code-drawn illustrations, animations, and short films in nine hand-drawn styles. Includes a TypeScript rendering engine and workflows for PNG, GIF, WebM, MP4, and standalone HTML output.

Skills | TypeScript · agent-skill · creative-coding

Python MCP server that exposes Synology NAS operations (file system, shares, downloads, iSCSI/NFS, users) as tools for Claude, Cursor and Continue. Ships Docker and PyPI installs plus stdio, Streamable HTTP and Xiaozhi WebSocket transports.

MCP | Python · mcp-server · synology

Kasetto manages AI agent environments from a declarative YAML config, syncing version-locked skills, commands, instructions, and MCPs across agents such as Claude Code, Cursor, Codex, and Gemini CLI. It supports shared team configs, secrets, and project or global scopes.

AI Agents | Rust · agent environments · skills

A browser-based AI film maker that turns a topic and chosen character into a narrated, animated short film. It generates scripts, images, video shots, voice, music, edits, and subtitles using fal.ai; users provide their own fal key.

AI Tools | TypeScript · AI video generation · storytelling

An MCP server that gives AI coding agents a persistent work item graph with dependency edges, phase-based quality gates, required notes, and actor attribution enforced server-side. Works with any MCP client; ships as a Docker image with an optional Claude Code plugin.

MCP | Kotlin · mcp-server · task-management

Local semantic code index exposed as an MCP server (plus ocbi CLI) for Claude Code, Codex, OpenCode, Pi, and other hosts. Combines embeddings, BM25, branch-aware incremental indexing, symbol lookup, and a call graph via Rust/tree-sitter, with Ollama, OpenAI, or Google embeddings.

MCP | TypeScript · semantic-search · code-search

Zero-dependency Python CLI that acts as an MCP client/decoupling layer: it keeps MCP tool schemas out of agent context (255 tools drop from 71,929 to 581 tokens, measured), unifies one MCP config across Claude Code, Cursor, Codex and scripts, and can expose every server as a single stdio server.

MCP | Python · mcp-client · token-optimization

A Python MCP server that exposes Windows desktop automation, shell, file, and system-management tools to compatible AI clients. Runs on the Windows machine and supports authenticated remote access.

MCP | Python · Windows · desktop automation

An MCP server exposing 151 security-analysis tools to AI clients for reverse engineering, malware analysis, forensics, vulnerability research, and SAST. It integrates tools including Radare2, YARA, LIEF, Capstone, and Volatility3.

MCP | Python · MCP server · reverse engineering

Story UI adds an AI-powered workspace to Storybook that generates repository-ready stories using components discovered in your project. It supports multiple LLM providers and checks generated screens in a real browser.

AI Coding | TypeScript · Storybook · code generation

An MCP server that exposes 98 tools for automating native Safari on macOS through AppleScript and JavaScript. It lets AI agents use an existing Safari profile, including its logins and cookies, for browsing, form automation, screenshots, and data extraction.

MCP | JavaScript · Safari · browser automation

Native iOS/watchOS LLM client in Swift: runs local GGUF models offline via llama.cpp or connects to OpenAI, Claude and Gemini. Adds session-level Chat/Agent modes, MCP tools, Agent Skills, an embedded Alpine Linux sandbox, Browser Agent, local SQLite RAG memory and two-way device sync.

AI Tools | Swift · ios · watchos

Third-party X (Twitter) scraping API with server-side tweet/profile filters, bulk exports, monitors and webhooks, delivered through REST, TypeScript/Python SDKs, CLI, a hosted MCP server and bundled agent Skills for Claude Code, Codex and Gemini CLI.

MCP | JavaScript · twitter-api · x-api

A local-first MCP server that indexes documentation by heading and retrieves byte-precise sections for coding agents. Supports lexical BM25 search by default, optional semantic or hybrid search, and documentation health and OpenAPI tools.

MCP | Python · documentation retrieval · section indexing

Local-first MIT proxy that sits between AI agents and model providers, pricing every request and rolling cost up per run, agent, and model. Adds budget caps, a kill switch, anomaly detection, complexity-based model routing, and cross-provider failover behind one Anthropic/OpenAI-compatible base URL.

AI Tools | TypeScript · llm-proxy · cost-tracking

Elixir AI runtime for building tool-using Jido agents. Provides ReAct loops, eight reasoning strategies (CoT, ToT, GoT, TRM, Adaptive), model routing across Anthropic/OpenAI/Google, telemetry, and policy/quota plugins.

AI Agents | Elixir · llm · agents

AgentQuant is a Python research platform where a ReAct LLM agent proposes trading strategies, backtests them with walk-forward validation, reflects, and stores results in cross-session memory. It evolves its own search harness across epochs under quality gates; the zero-key demo runs offline.

AI Agents | Python · quantitative-trading · agentic-ai

ZeroID is a Go-based identity server giving autonomous AI agents their own credentials: OAuth 2.1 issuance, RFC 8693 on-behalf-of delegation with scope attenuation, SPIFFE/WIMSE identities, DPoP, attestation, and cascade revocation for agent chains and MCP servers.

AI Agents | Go · agent-identity · authentication

TokenPrint renders a real LLM forward pass in interactive 3D: attention heads, RoPE, GQA and the residual stream traced from actual tensors or a local GGUF file. Four modes (architecture, generation, walkthrough, debugger) with provenance tagging. Runs a FastAPI backend plus a Next.js/Three.js frontend.

AI Tools | TypeScript · transformer-visualization · llm-interpretability

A curated directory of Jev demos, SDKs, skills, and integrations, with source links, recorded examples, and notes on setup and limitations. Covers browser and computer-use agents, MCP tools, coding-agent integrations, and other typed-decision applications.

AI Tools | Python · awesome-list · Jev

A Codex and Claude Code plugin for 1C:Enterprise development. It provides agent skills and an MCP server for creating and validating metadata, building forms and reports, searching BSL code, and running 1C operations.

AI Coding | Rust · 1C:Enterprise · Codex plugin

An curated directory of blueprints, tools, research, and guides for building LLM-compiled knowledge bases. Covers agent-maintained Markdown wikis, persistent memory, graph-based approaches, and comparisons with traditional RAG.

RAG | LLM wiki · knowledge bases

OctoBus is a single Go binary that runs locally as a gateway, importing Node.js service packages and exposing selected gRPC methods to agents via MCP, Connect RPC, and gRPC through scoped capsets and tokens. It adds authorization, SQLite-backed state, and runtime management for approved enterprise tool calls.

MCP | JavaScript · agent-tools · api-gateway

WinDbg-style Windows kernel and user-mode debugger that runs on Linux and macOS via KDNET, KVM/QEMU, VMware, UTM or offline crash dumps. Ships a Python SDK, DAP editor integration, and an MCP server, but it is a debugging/reverse-engineering tool, not an AI product.

MCP | Rust · windbg · kernel-debugger

Wavefront is an open-source middleware platform for building and operating enterprise AI agents, workflows, and RAG applications. It provides data integrations, MCP connectors, access controls, and observability.

AI Frameworks | Python · AI middleware · AI workflows

Rust agentic browser driver exposing 5 MCP tools (act, see, state, run, vision) over CDP, with 6-layer stealth, delta-first token output, and re-render-immune refs. Single zero-dep binary for Linux/macOS/Windows, also usable as a CLI.

MCP | Rust · mcp-server · browser-automation

Javis OS is a self-hosted agentic AI platform: an MCP-equipped agent with swappable LLM backends (Claude Code, Codex, Gemini, Ollama, OpenRouter), a persistent Second Brain, skills, background loops, Kanban task delegation, knowledge graph, voice chat and a web dashboard.

AI Agents | Python · agent-os · agent-orchestration

A collection of installable agent skills for Meta Quest and Horizon OS development, covering app creation, SDK upgrades, UX, and performance. Includes the metavr CLI and an MCP server with tools for device management, app control, and documentation search.

Skills | C# · agent-skills · Meta Quest

pi-go is a Go terminal coding agent built on Google ADK Go: multi-provider LLM routing, sandboxed read/write/shell/git tools, LSP, subagents, MCP/skills extensions, session persistence, and a 4-layer SQLite memory palace. MIT-licensed, TUI plus print/JSON/RPC modes.

AI Coding | Go · coding-agent · terminal

A collection of C#/.NET examples for building and using MCP clients and servers. Includes sample servers for Markdown conversion, Outlook email, to-do lists, and GitHub Copilot customization files.

MCP | C# · .NET · MCP server

Simulates a camera-only quadrotor navigating an obstacle course in MuJoCo. A Jev judgment model proposes tactical maneuvers while conventional control and safety code retain flight control and veto authority.

AI Agents | Python · autonomous-drone · robotics

Lexora is a local-first desktop AI agent (Vue + Electron + a separate TypeScript runtime, Rust native layer) that runs an agent loop with sandboxed tool execution, MCP integrations, Skills and scheduled tasks. It is model-agnostic and requires explicit user authorization for file and tool access.

AI Agents | TypeScript · desktop-agent · autonomous-agents

MCP server that connects AI agents to ITASCA geomechanics engines (PFC, FLAC, 3DEC, MPoint, MassFlow). Exposes 5 documentation tools and 5 execution tools (REPL, task submission, monitoring, history) so agents can run geotechnical simulations and query versioned engine docs through natural conversation.

MCP | Python · mcp-server · geomechanics

Python toolkit and CLI for auditing and optimizing web content for citations in AI search engines. Includes a content analysis, ranking, rewriting, and schema-generation pipeline, plus Claude Code skills, MCP support, and an evaluation harness.

AI Tools | Python · generative engine optimization · answer engine optimization

A self-hosted AI office agent for desktop, web, and CLI that plans and executes tasks, then verifies deliverables such as PPTX, DOCX, XLSX, and websites. Supports configurable LLM providers, Ollama, Claude Code, Codex, MCP, skills, and scheduled messaging workflows.

AI Agents | JavaScript · AI agent · office automation

Jacobian is an MCP server exposing a searchable vocabulary of typed mathematical operations: math.find matches or inspects an operation contract, math.run executes it and returns exact typed results. Also usable via CLI and a Python API, backed by SymPy, NetworkX, Z3 and python-flint.

MCP | Python · mcp-server · math

A DeepSeek Harness plugin that puts a second, read-only reviewer subagent on the approval chain: it inspects tool arguments and workspace evidence, returns structured allow/deny verdicts with reasons, and fails closed by default with a full session-log audit trail.

AI Agents | TypeScript · ai-safety · approval

Cross-platform Electron runtime and MCP gateway exposing 253 tool definitions (files, Git, processes, browser, Windows/WSL automation) to AI agents and clients like ChatGPT, Claude and Codex via stdio, loopback, ngrok or OpenAI tunnel transports.

MCP | TypeScript · mcp-server · mcp-gateway

Open, cited oncology knowledge graph delivered as a Next.js site, static JSON API, MCP server, CLI and WebMCP tools. Primarily a domain data corpus about cancer; its MCP/CLI/LLM-context surfaces let agents search treatments, trials and institutions.

MCP | TypeScript · oncology · cancer

Python SDKs for loading tools from an MCP Toolbox server and using them in custom applications or with Google ADK, LangChain, LangGraph, and LlamaIndex.

MCP | Python · Python SDK · MCP client

A SwiftUI package of nine animated, dotted 3D indicators and status labels for AI and agent interfaces. Supports state-specific designs, adjustable sizing, accessibility features, and pausing when offscreen or in the background.

AI Tools | Swift · SwiftUI · loading indicators

Pure Rust PDF toolkit whose headline feature is structure-aware RAG chunking: each chunk carries pages, bounding boxes, element types, heading context and token estimates, with no ML or C dependencies. Also parses, generates, encrypts and validates PDFs in one crate.

RAG | Rust · pdf · chunking

An end-to-end AWS reference architecture for a multi-agent chatbot built with Strands Agents and Bedrock AgentCore. Demonstrates MCP and A2A tools, persistent memory, browser automation, voice, skills, and Terraform deployment.

AI Agents | Python · multi-agent · agentic-chatbot

Zafiro is a BYOK AI agent for Android that can interact with apps and control the device through Shizuku or root. It supports MCP, skills, memory, on-device Python and shell tools, and SSH to remote machines.

AI Agents | Kotlin · Android · phone-use

Agent Kernel is a Python platform layer for running, orchestrating and deploying production AI agents. It runs OpenAI Agents SDK, LangGraph, CrewAI and Google ADK side by side, adds guardrails, sessions, RAG, sandboxing, channels and MCP/A2A/AG-UI, and deploys to AWS, Azure, GCP or Kubernetes via Terraform and Helm.

AI Frameworks | Python · ai-agents · multi-agent

Self-hosted AI agent workspace in Node.js/Vue 3/Electron with tool calling, MCP connectors, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered in Three.js.

AI Agents | JavaScript · ai-agent · self-hosted

MartinLoop is a governed runtime and CLI for AI coding agents. It adds budgets, iteration caps, edit scope, verifier checks, rollback evidence, and run receipts across Codex, Claude Code, and MCP hosts.

AI Coding | TypeScript · ai-coding-agents · agent-governance

Enterprise multi-agent platform built on AgentScope: orchestrates delegating expert agents for ChatBI (text-to-SQL over Oracle/ClickHouse/MySQL), RAG knowledge Q&A, MCP tool use, multi-policy sandboxes, browser automation, RBAC, and scheduled notifications.

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

Self-hosted platform for creating and coordinating company agents powered by Claude Code, Codex, or local models. Agents can use tools, memory, knowledge and skills, work on schedules or webhooks, delegate tasks, and build apps.

AI Agents | Python · multi-agent · self-hosted

MCP server that turns prompts into versioned YAML templates, composable multi-step chains, and validation gates via an operator syntax (>>, ::, @, #). Authors resources once and exports them as native skills for Claude Code, Cursor, OpenCode, and Gemini CLI.

MCP | TypeScript · mcp-server · prompt-templates

Single-binary Rust gateway that routes team chat channels (Slack, Teams, Telegram, Matrix) to untrusted autonomous LLM agents with per-channel isolation, credential vault, tiered permissions, sandboxed exec, MCP proxying, and a signed hash-chained audit log for SIEM.

AI Agents | Rust · agent-gateway · mcp

An MCP server that indexes searchable, sourced documentation for 26 football data providers and tools. AI coding agents can retrieve API details, compare provider conventions, and resolve entity IDs instead of relying on potentially outdated model knowledge.

MCP | TypeScript · football data · soccer analytics

Official MongoDB agent skills pack that gives coding agents guidance on queries, schema design, query optimization, Atlas Search and Vector Search. Bundles MCP server configuration for Atlas (OAuth) or self-managed deployments, installable via Claude, Cursor, Codex, Copilot, VS Code and Grok plugin marketplaces.

Skills | TypeScript · agent-skills · mongodb

Go-based MCP server exposing Kubernetes and Helm operations (list, describe, logs, metrics, create/delete, Helm releases) as MCP tools. Runs in stdio, SSE or streamable-HTTP mode with read-only and tool-category flags, plus kubeconfig, token or in-cluster auth.

MCP | Go · mcp-server · kubernetes

trace-mcp is a framework-aware code intelligence MCP server that indexes a repo into a dependency/knowledge graph once, then serves tools like get_change_impact and plan_turn to agents, cutting PR-review input tokens by 72.7%. Works with Claude Code, Cursor, Codex, and any MCP client.

MCP | TypeScript · mcp-server · code-intelligence

Local-first project management app with a CLI, web UI, MCP server, and skills for coding agents. Agents can manage tasks and project knowledge while their actions are recorded in an activity feed.

AI Tools | Go · AI agents · project management

Apache-2.0 robotics simulator for AI coding agents: Newton physics with wgpu rendering, a 38-endpoint HTTP/JSON harness and a first-party 37-tool MCP server so Claude Code or Cursor can program, run and debug simulated robots. Ships ROS 2 sidecar, URDF/STEP digital twins and 52 demo worlds.

MCP | Python · robotics-simulation · mcp-server

OWASP Agent Memory Guard is a Python runtime defense layer that sits between an AI agent and its memory store, screening writes/reads for prompt injection, memory poisoning, secret leakage, protected-key tampering and self-reinforcement loops. It enforces YAML policies, emits audit events and ships drop-in integrations

AI Tools | Python · agent-memory · ai-security

Provider-agnostic CLI that scaffolds a structured multi-agent coding harness into your repo: shared task backlog, role-based agents, SQLite audit trail, health gate, and a local MCP server that Claude Code, OpenCode, Codex, or Grok can connect to. Stored locally, no cloud or API keys beyond your existing AI tool.

AI Agents | TypeScript · multi-agent · agent-harness

Local-first Kubernetes desktop workspace built with Tauri v2, React 19, and a pure-Rust core for SREs. Its main AI angle is a built-in MCP server that exposes cluster capabilities over stdio or loopback HTTP, with destructive tools confirmation-gated. Dependencies:

MCP | TypeScript · kubernetes · mcp-server

A Rust framework for building tool-using LLM agents, with streaming support across seven protocols, built-in tools, MCP and OpenAPI integrations, sub-agents, and session management. Includes a terminal coding-agent example.

AI Frameworks | Rust · agent loop · tool calling