Autonomous AI agents that perform tasks independently
bakw00ds
Multi-runtime agent framework (Claude Code, Codex, Antigravity) with hard/soft controls, audit-first hooks, and multi-dev coordination.
...moreOpendray
Self-hosted gateway for AI coding agents (Claude Code · Codex · Gemini · shell). Remote-control sessions from web / mobile / messaging apps — Telegram, Slack, Discord, 飞书, 钉钉, 企业微信.
...moreKuonirad
Verifiable reasoning substrate for reproducible agents: deterministic orchestration, Merkle provenance, and positive-impact audits.
...moreAgentRoom Contributors
A lightweight local multi-agent AI collaboration platform
Mikko Korpela, Uzair Ahmed
LangChain integration for Adeu — track-changes for DOCX in the LLM era
xuda.io
Xuda Dashboard Controller Agent
myccaig
TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforcement.
...moreGitHub Actions
Opinionated skills, hooks, and workflows for AI agents
AgentGuard Team
AI Output Safety Middleware — the seatbelt between LLMs and your systems
johangar5
The official TracePilot AI SDK. Time-travel debugging, observability, and tracing for autonomous AI agents.
tesserathetoken
Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m
...moreanantdhavale
JavaScript SDK for checking AI agent actions before they run.
Local dashboard observing SDD workflows in Claude Code
hjw
LLM Agent experimentation harness for SWE tasks
agencyflow-hq
Official HTTP client for the Mnemix memory + enrichment API for AI voice and chat agents.
rayyankhan27
AWI (Agent Web Interface) SDK — deterministic browser automation for AI agents
Phionyx evaluation tooling — LLM-as-judge primitive (eval-side) plus the assessment-signal vocabulary from the Phionyx Evaluation Standard v0.2.0. Producers run a judge against a (claim, evidence, rubric) triple and emit a signed Judgment envelope. Caller supplies the LLM client; no hard dependency on any provider SDK.
...moreBaidu Cloud SDK
Baidu Cloud vpcApi SDK Library for Python
geoff
LangChain adapter for Flotilla
geoff
SQL-backed durable storage implementations for Flotilla
Runtime security firewall for LangChain agents — intercepts tool calls, enforces YAML policy, logs to SQLite.
xuanlinAI
玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置
adityaarsharma
Self-hosted SEO crawler for Claude — Screaming Frog-level audits, unlimited pages, 1-click install. 19 MCP tools.
epicsagas
Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, autonomous spec-to-PR pipeline. Works with Claude Code, Codex, Cursor, OpenCode, and Cline.
...more