#agent

Self-evolving skills lib for coding agents

Code research platform for AI agents: local + GitHub search, LSP semantics, AST patterns, and compact context. one toolset as MCP or CLI

PHP client for consuming Strands AI agents over HTTP - invoke, stream via SSE, manage sessions

CLI for the Clear Street API

An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay

Gives agents a think→act loop — plus recursive decomposition (RLM): break a hard task down, fan out, verify, synthesize. Goal in, coordinated actions out. Replaces LangChain, CrewAI, AutoGen. Zero required deps.

A modern Go framework for building multi-agent AI systems.

A faster, lighter, cheaper alternative to sandboxes. Run any coding agent inside an isolated Linux VM, with agent orchestration built in.

A faster, lighter, cheaper alternative to sandboxes. Run any coding agent inside an isolated Linux VM, with agent orchestration built in.

MCP server + CLI giving AI agents 50 spreadsheet tools for .xlsx — live-recalc formulas (~390 Excel functions), repair broken references & external links, read/write, diff, and audit. Works in Claude Code, Cursor, Codex, and any MCP client.

A minimal, composable Go library for building AI agent applications.

📂 Web File Browser | Server Manager | Server Ai Agent | 文件服务器 | 内网穿透

A cli for loops

MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

Anti-hallucination AI agent kit for Cursor, Windsurf & Antigravity. 27 specialist agents, 17 slash commands, 8 Tribunal reviewers. Install: npx tribunal-kit init

Web research for pi with smart and safe tooling + agent system

Local-first tool that autonomously turns GitHub issues into pull requests — backlog/queue board, CI babysitting, auto-merge, and cost tracking.

This is a collection of opinionated linting rules (in Biomejs) for Effect-ts projects

🔧 Repair JSON！Solution for JSON Anomalies from LLMs.

Own your agent. Run tasks, use wallets, and mine.

Agentic finance infrastructure.

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

An AI assistant runtime for coding and team workflows, with DingTalk AI Cards, sub-agents, memory, and scheduled events.

iMessage adapter for Chat SDK. Supports both local (on-device) and Photon iMessage integration.

Shared installer SDK for bundled Agent Skills.

AI-powered product lifecycle orchestrator — takes a product idea from intent to shipped code through agent-driven pipelines (Claude + Codex) with human gates, postconditions, and auditable traces.

Vendor-neutral control plane for AI coding agents. Deterministic CLI surface for context fetch, verify, and progress. Stable in v1.0 for claude-code / codex / generic; cursor / gemini-cli experimental.

Multi-project agent orchestration for Claude Code. One command session controls everything.

The most powerful Package Manager for Agents Skills: search, query and install/uninstall in seconds!

Open-source AI Agent platform — 80+ MCP tools, 7 channels (Slack/Discord/LINE/Telegram), Rust + Python. Self-hostable Claude/GPT alternative for production multi-LLM systems.