Autonomous AI agents that perform tasks independently
subhajit60
A TypeScript AI Agent Framework
vietor
Lightweight AI agent framework — session orchestration, tool system, MCP client/server, skill loader
risshabs22-quantified
AST-based token optimizer that trims codebase context for AI agents to eliminate context-window bloat and cut LLM API costs.
...moremegaphone-tokyo
AI進捗管理カンバンダッシュボード — CLI型AIエージェントのタスク進捗をローカルのカンバンボードで管理する
pcruiher08
Autopsy your coding-agent sessions — see every tool call, token, and dollar
Jonathan Melton
Audit and scaffold AI harness configs for Claude Code and Hermes Agent — score your setup out of 100
SciModelingBench contributors
An observation-grounded benchmark framework for scientific modeling and design.
aisona-lab <[email protected]>
Audit Agent Skills and packages before they touch your machine. Deterministic checks. Exit codes. No vibes.
Sjors Robroek
A bundled copier conductor skill — the bailiff fills in the paperwork; copier makes the copies.
xuzhougeng
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
...moreCavibora
Model-agnostic AI coding agent for your terminal - 22 tools, 5 LLM providers, multimodal, 8 languages
WGJ-Fry
Open-source, self-hosted, local-first personal AI assistant and private second brain with memory, mobile access, and generated problem-solving tools.
...moreLunamos
Give your original character a computer to live in — an open-source runtime for persistent, autonomous AI characters. SillyTavern-compatible cards, real tools, a real sandbox.
...moreSpencerRaw
A Hermes Agent skill for stand-up comedy writing. Guided 5-step framework: Attitude → Insight → Explanation → Defamiliarization → Scenarization.
...moreXuepoo
A powerful LLM-driven agentic EPUB book translator with robust progress monitoring and recovery
chenhangcuisg-code
GAT — Godot Agent Team: a full-cycle (design→implementation) Godot game-dev agent. Style-locked asset generation, self-evolving knowledge base, runs under both Claude Code and Codex.
...moreRyan
Agent Organization Infrastructure for governed multi-agent engineering work
Pranjalab
Leave your desk — Claude Code keeps working and reports to your phone over Telegram.
Cut AI agent token costs. One line of code. Drop-in supervisor for LangChain, LangGraph, AutoGen, CrewAI, and Smolagents.
...moreclidey
Where data access meets operational intelligence
Spectron agent memory for the OpenAI Agents SDK
GitHub Actions
AI Agent Skill 集中化管理 CLI 工具
minhlotics
Lotics SDK and CLI for AI agents
yuwang26
Markdown → one .paged.html print document that edits itself in the browser and exports to PDF by printing (paged.js). Source rides inside the file, saves in place. Ships agent skills.
...more