Autonomous AI agents that perform tasks independently
Minimal harness engine for building LLM agent apps (C++ + pybind11)
Joe Robinson
A lightweight agent runtime that turns any machine into an AI-agent-ready compute target
Muthukumaran S
COIL - Token-optimized structured data encoding for LLM pipelines. Compress JSON into compact, schema-aware blocks that reduce LLM token usage by 40-70%.
...morekeryilmaz
Knowledge layer for AI agents — scan your repos, give every agent a map of your system.
tuandm
Token-efficient browser CLI for AI coding agents. Persistent headless Chromium with ARIA refs, CSS inspection, auth profiles, and 50+ commands. ~50-100 tokens per call vs ~1500 for MCP tools.
...moreswarmclawai
Self-hosted multi-agent AI runtime with MCP server support. Build, orchestrate, and run autonomous agents with memory, skills, schedules, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama).
...moreBuddyAI CLI — LLM-driven agentic framework powered by Claude
ArtemisAI
Android phone control for pi-agent — 36 tools to see, touch, and automate any device via ADB
VitruvianSoftware
A macOS menu bar app and Telegram bot bridging your messages to local AI coding CLI tools, giving you remote access to agentic capabilities from any device.
...morenoah-sheldon
Production-ready AI dev workflow scaffold with 59 skills, 33 agents, hooks, and rules for Claude Code, Codex, Gemini CLI, Copilot CLI, Qwen Code, and OpenCode.
...moreRobThePCGuy
Markdown Agent Studio is a workspace where agents develop specialization through their own experience.
launchapp-dev
Autonomous AI agent orchestrator — run multi-model dev teams (Claude, Gemini, GPT) with YAML workflows, daemon scheduling, and MCP integration. 100% Rust.
...morestrewerwer
🔍 Enhance retrieval with the Agentic RAG Framework for hybrid search, query classification, and answer fusion in production-grade systems.
...moreachankra
Agentic AI in Platform Engineering Cohort #2 O'Reilly
shahzebqazi
Central Mac bootstrap hub — master config, satellite repos, Cursor-first workflows.
kingbee-helix
Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.
karstom
A lightweight, framework-agnostic persistent memory graph for AI coding assistants.
kumo-ai
Kumo Coding Agent — context docs, skills, and self-maintenance for building ML models with the Kumo SDK
Claude Code adapter for axor-core governance kernel
Benchmark governed vs raw Claude on your codebase
aki1770-del
Parallel LLM scout + confidence-gated synthesis loop for GitHub-grounded research
OpenTelemetry integration for AI coding agents (Cursor IDE/CLI, GitHub Copilot, Claude Code, Antigravity, OpenCode-compatible runners)
...morememory-keeper contributors
Session-close memory distillation for Claude Code
Open-source benchmark for LLM inference on agentic swarm workloads