Autonomous AI agents that perform tasks independently
WIndFate
Production-grade legal AI agent reference implementation — LangGraph + pgvector RAG + MCP + 9-language i18n. Engineering case study (non-commercial, JP Attorney Act §72).
...moreagentic-chaos Contributors
Standalone fault injection toolkit for LLM calls and agentic workflows, with an optional AgenticLens integration.
Zansn Labs
Turn OpenAI Agents SDK runs into portable Zansn evidence packs. Capture traces, tool calls, cost, and readiness from a run result.
...moredmae
General-purpose agent with transport abstraction, state management, and attachment support
igorkosta
Agent Skills Manager — install, update, and manage AI agent skills
unirateapi
LangChain.js integration for the UniRate currency-exchange API. UniRateAPIWrapper + three structured tools (exchange, rate, currencies) ready to plug into any LangChain.js agent. Zero runtime deps; peer deps only.
...moresoovwv
AI workspace coordination tool with an env map and light SBOM for multiple AI agents sharing one development environment.
...moreduyuan
A personal AI Agent like OpenClaw, including tools, skills, memory, hook, sub-agent, MCP sever, etc. Run in the terminal.
...morevotee_tech
30 AI agent skills for data science and computational linguistics
Lightning AI sandbox integration for Deep Agents
lyx
Shareable ESLint flat config for AI-generated TypeScript: type safety, Promise safety, Temporal-only dates, and inlined agent guardrails.
...moreRobinAgents
Prime Agent CLI for RobinAgents — autonomous GTM agents on Robinhood Chain
Tarek Awwad
Reserved for the Check Your Agent project — https://checkyouragent.dev
Julia Edomskikh
Agent: text / field layout -> dashboard in selected BI on top of DWH DM layer
"M. Abubakar" <[email protected]>
AI Agent that auto-generates Postman Collections from backend code
ACP (Agent Client Protocol) entry point for gptme — lets editors like Zed and JetBrains launch gptme via uvx
AgentCulture
Hosted platform running the League of Agents arena online at https://league-of-agents.ai — a turn-based game for humans and agents, for fun and for benchmarks. Continuable matches, AWS-hosted, with safe-capacity safeguards and price-aware archive/cleanup. The league-site CLI is the local operator surface and how agents work with it.
...morePlanContract Contributors
Framework-agnostic schemas and validators for multi-agent turn routing plans
Run-scoped LLM observability control plane backed by LiteLLM
AxioRank
AxioRank middleware for LangChain agents: govern every tool call and model turn through one Zero-Trust security gateway.
Cloud Dancer
Persistent memory for AI coding agents — works with Claude Code, Cursor, Codex, ChatGPT, Grok Build, and other AI coding assistants. A long-term context substrate on disk plus a multi-agent kanban board: sessions survive compaction, restarts, and /clear, and stop re-explaining the project. Installs the `celeborn` command.
...moreKynth Studios
Kynth Core tools for CrewAI — document parsing, chargebacks, contracts, dunning, lead screening, and cited research as ready-made BaseTools.
...moreSelf-healing runner for Python projects: catches crashes, remembers them, and patches them on the fly with a headless Claude agent.
...moreCiphemon
Zero-token structural verifier for agent loops: one choke point at the submit boundary enforcing grounding and budget invariants. No LLM calls, stdlib only.
...more