#ai-agents

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Agentic coding in your terminal,Simultaneously compatible with OpenAI, Gemini, and Claude.运行在终端的 AI 编程智能体，同时兼容 Deepseek、OpenAI、Gemini和Claude。

One CLI to manage AI agent plugins and skills — author once in a single manifest, adapt to Claude Code, Codex & Antigravity. Versioned & reproducible.

Astrology API SDK for TypeScript. The Spiritual OS layer: Western, Vedic, tarot, numerology, human design and 18+ domains, one key. Fully typed, MCP ready.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.

Python SDK for The Colony (thecolony.ai) — the official Python client for the AI agent internet

Development tools backing a-novel and a-novel-kit. Home of the a-novel CLI and AI skills.

An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.

AnchorBrowser-SDK-Typescript

Database Reporting Tool and Tasks (.Net)

23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

Find what broke in your agent calls. Pin it so it never ships again. Local voice-agent call forensics and regression guards.

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

Governed AI agent orchestration for Claude Code and Codex: 17 squads, 172 agents, software delivery workflows.

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Governed, provider-agnostic Python agent SDK: cost budgets, tamper-evident audit, and PII redaction built in.

Every agent turn becomes a traceable commit carrying the full interaction trace, model, and token cost, plus a live dashboard and a coach that teaches you, from your own sessions, to drive agents and your codebase better.

Ollama model provider and utilities for adk-go

Token-Reducing Shell — terminal output compression for AI coding agents

Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers

🧾 Agentspecs — YAML-based specifications for AI agents, MCP servers, Skills, Guardrails and more...

Autodesk 3ds Max MCP adapter for AI agents to inspect and edit scenes, automate modeling and animation, and use verified undo through the DCC-MCP ecosystem.

SideFX Houdini adapter for the DCC Model Context Protocol

Detent is board-driven agentic work orchestration, shipped as a single Go binary — it watches a GitHub Projects board and runs each ready issue through an isolated Git worktree, a coding agent, your validation gate, and a serialized merge train, live on web and terminal dashboards.

No repository description published.

⚡ High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx