Autonomous AI agents that perform tasks independently
ownware-ai
The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.
Trey Goff
A tiny CLI for delegating bounded agent tasks to Cursor, Droid, OpenAI Codex, Claude Code, Grok Build, or Kimi Code runtimes.
...moreFind out whether your AI agent's evals are lying to you: stability reports with flip attribution, LLM judge audits, and deterministic checks mined from your KB.
...morepalash76
Kakunin compliance tools for LangChain JS/TS — verify agent certificates and scopes inside tools and chains
ajnasnb
Maqam is an MIT-licensed agent framework for governed workflows, policy, evidence, skills, CLI workers, and crawler-backed research.
...more0xdivyanshh
TypeScript SDK for AI agents to take and repay revenue-underwritten credit on TrustLine (Stellar). Settles in USDC.
Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget
...moreRafael Pena
Zero-trust repo intake for AI coding agents: scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo.
...moreAlphaAgent contributors
Multi-agent stock & crypto screening with leakage-aware (point-in-time) LLM evaluation and an honest, mechanical backtest.
...morepr-genius contributors
Evidence-backed lookup for big-repo PR contributions. Local-only, zero-runtime, stdlib-first. Renamed from `prgenius` to avoid PyPI name collision with an unrelated 2024 GPT-3 PR-description tool. Distribution renamed again in v0.7.8: `prgenius-kb` → `prgenius-core` (aligned with `misakanet-core` convention).
...moreAgentOps
Multi-agent orchestration backend — FSM pipeline, workflow engine, and agent bus on one substrate
ronghua
LangChain tool for PayPack: AI Agent autonomous payments (HTTP 402, x402, AP2)
xinhuang
A general-purpose Python framework for building LLM agents and multi-agent systems, with tools, memory, retrieval / RAG, context engineering, guardrails, human-in-the-loop, and observability.
...moreGitHub Actions
Local-first memory + knowledge layer for AI agents.
Ldxs (wUwproject)
本地 RAG 智能体 — 基于嵌入向量路由的多知识库问答系统
UiPath
Evaluate, benchmark, and A/B-test AI coding agents (Claude Code, Codex, Gemini/Antigravity) with sandboxed, reproducible YAML task suites.
...moresainigurnoor511
n8n community node for the AI Voice Agent from SuperHippo — create leads, trigger calls, and react to call outcomes.
pexuleco
n8n community node for Clinicorp (dental & clinic management SaaS): estimates, patients, appointments, financial, payments, sales, procedures, professionals, clinics, CRM leads, analytics and more. Usable as an AI Agent tool.
...morePraash
Record-replay debugger for AI agent runs
Nathan Green <[email protected]>
Multi-agent LLM communication system with ensemble orchestration
GitHub Actions
Infer a Google Maps reviewer home region and footprint from their review history. Apify-backed n8n community node, pay-per-result, and usable as an AI agent tool.
...moresongdongdong
Wukong Agent SDK — 可嵌入的 AI 编程 Agent 引擎（ReAct 循环 + 内置工具 + 技能系统），供其他应用以库方式集成
Inspect Robots contributors
LLM agent policy for Inspect Robots: frontier LLMs (Claude, GPT, anything OpenAI-compatible) drive any registered embodiment through tool calls.
...moreEnterstellar
DEPRECATED: This package has moved to @enterstellar. Update imports to the new scope.