Autonomous AI agents that perform tasks independently
GitHub Actions
Pay-per-skill package manager for AI agents
patricklouback
An Nx monorepo built to be operated by AI agents: every app ships with an AGENTS.md that is generated from the project graph, not written by hand.
...moreGitHub Actions
Transparent optimization runs for AI agents
mhai
AI agent CLI — support Anthropic & OpenAI-compatible API, zero dependencies
Agent-native ML experiment tracking and lineage/knowledge substrate
Omar Yousfi
Read-only Kubernetes incident diagnosis: deterministic detectors plus optional LLM root cause analysis (Anthropic, OpenAI-compatible or Ollama).
...morebsawang
Local-first token usage collector for AI coding agents (Claude Code): passive transcript scan, per-project stats, optional cloud sync
...moreA Python framework for building AI agents: typed streaming, tool loops, multi-agent handoffs, HITL approval, and DAG orchestration.
...moreFantasality
DSH Origin Plugin: drive OriginLab Origin scientific plotting from AI chat via MCP. 62 tools: modal-dialog watchdog, LabTalk safety gate, FigureSpec declarative YAML, fit params, matrix tools, matplotlib bridge, PPT assembly, editable OPJU delivery. Windows + Origin 2021+.
...moremrgoonie
Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.
...moremybay-ai
Local-first, self-hosted control plane for deploying, managing, and chatting with multiple AI agents. 本地优先、自托管的多 AI Agent 部署、管理与对话平台。
...morefong-foo
Event-Driven Cognitive Execution Engine for AI Agents — 612 lines of pure Python, zero dependencies. BM25 retrieval + 5-type classifier + negation detection. Deployed in production for CiteFlow's 3 AI Agents.
...morebradley.steinfeld
LangChain.js model adapter for LangECS — use any LangChain chat model as a LangECS Model
vour-crypto
药用植物次生代谢科研推理 LLM Agent:多组学分析流水线 + LLM 证据推理,确定性计算与 LLM 推理分层
kwakminoo
Open Source Desktop AI Agent Runtime - LLM, MCP, Voice Runtime, and local/cloud models wired into one PyQt6 desktop agent (Ollama + Hermes)
...moreBinary Glide
Statistical Process Control for LLM-as-a-judge agent quality scores
Infyrence
A zero-dependency, SIMD-accelerated LLM framework built for speed, safety, and scale.
263311487-ux
The scientific thinking protocol for AI agents — falsify before you believe. 5-stage falsification skill (axioms → hypothesis → adversarial → verify → converge) for Codex, Claude Code, Cursor, Gemini CLI & 20+ agents. Dual-model evals 26/28. 五段式科学思维协议：公理
...morebalaguru-nilacandane
A local-first AI agent for your terminal. Think. Remember. Act. Observe.
1mingji1
Xiao Zhi CLI（小智）：一个简单的终端 AI Agent，支持 OpenAI 兼容接口（Ollama / DeepSeek / Kimi 等）和工具调用
robotlearning123
A coding-agent terminal for the GLM engine — streaming TUI, tool calls, checkpoints, quota insight; drives your installed ZCode runtime on your own Coding Plan.
...moredev-sergeev
Local chat UI for OpenAI-compatible and GigaChat models with persistent history
caglarbaranbora
Installs the Apple Agent Kit Claude Code plugin via the claude CLI.
AI Foundry Ventures
Warrant: the decision ledger for AI agents. Record every consequential agent action with its mandate, evidence, cost and outcome, and replay real decisions before you ship a change.
...more