Autonomous AI agents that perform tasks independently
nzt6624
Shared FamilyPlate agent tool registry and scope definitions.
mindpal-admin
MindPal Device Agent SDK - Build intelligent device agents with plugin architecture, secure handshake, and multimodal capabilities
...moreNUHASHROXME
Multimodal Agentic RAG with hierarchical tree indexing — index PDFs & Markdown into navigable tree structures, persist in Supabase, and query with LLM-powered retrieval.
...moreGeneric attribute templates (personality / speech / archetype / visual / hobby) for composing AI-agent character personas
...morelianluo-esign
Open-source Rust/Pingora AI gateway and reverse proxy for self-hosted LLM traffic control: OpenAI-compatible Chat/Responses, provider routing/fallback, virtual API keys, policy and budgets, exact-match cache, MCP/tool execution, observability, Admin APIs/dashboard, cluster ops, and automatic HTTPS.
...moretechnosiveuk-ui
The Open-Source MCP Firewall & Security Gateway for AI Agents. Inspect, redact, and control tool calls. Proxy mode (universal) and Inline SDK mode (Go).
...morezmysysz
A powerful command-line tool for browser automation, designed specifically for AI agents and automated workflows.
sandydasari
An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.
...morejakbuczarnecki
Harness AI & Agent OS for governed multi-agent systems in Python — Nexus orchestration, policy, tools, skills, RAG & multimodal evaluation. Prototype fast, harden agents for production.
...moremonahright467
Explore harness engineering books for building bounded, accountable code workflows in terminals, repos, permissions, and team systems
...moreyzfly
为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好。 | Born to burn tokens — they get cheaper, quality stays scarce. A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best. Claude Code-style, any model, team-ready.
...moredwgx
AI QQ bot with OneBot, NapCat, LLM routing, plugins, and WebUI
Runnable AGENT.md compile loop for scriptorium: drives `scrip` via subprocess + Claude. Not part of the deterministic scrip core.
...morerag-agent-eval-ci contributors
CI evaluation framework for RAG and AI agents: groundedness, retrieval quality, hallucination, citations, latency, cost, and regression gating before production.
...moreMulti-agent framework for generating Rivet analysis routines using large language models
jukrap
Reusable AI agent skills, project playbook templates, and a small operator-controlled runtime harness.
aGiT contributors
Interactive agent + git commit orchestration. Requires git and a backend CLI (Claude Code or OpenCode); the GitHub CLI (gh) is optional, used for the dashboard's GitHub-ID committer view.
...moreGitHub Actions
Codex skill for committing current git changes in logical local groups.
weilueluo
TypeScript SDK for running autonomous agent sessions across providers (Anthropic, OpenAI, DeepSeek, Gemini, Mistral) behind one interface.
...moreGitHub Actions
GitHub as a knowledge graph for AI agents. Autonomous dev pipeline for Claude Code.
evsadmin
AI agent skills for Google Gemini — list, search, export Gemini chats and run structured debates with Gemini. Works with OpenCode, Claude Code, and any skill-compatible AI agent.
...moreGitHub Actions
Drop-in replacement for @anthropic-ai/claude-agent-sdk that adds OpenTelemetry instrumentation for Astro deployments.
vivekmind
Open-source terminal AI agent with full AWS Bedrock support. Bring your own keys.
c0hm
a thin, no-framework dashboard for OpenClaw Gateway. Real-time session monitoring, full event visibility, zero bloat. Minimum payload, maximum control.
...more