Sàn agent

Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.

Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)

WUPHF lets you spin up your personal office of AI teammates who collaborate over shared context. Supports Claude Code, Codex, OpenClaw, OpenCode, local LLMs.

DeepSeek Harness: Everything is a Plugin.

Reverse engineer anything with agents, from app behavior down to native binaries.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

Governance standard and reference toolset for LLM-maintained knowledge corpora

Harness-oriented agent system framework for production-grade LLM agent applications

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.

The most Token-efficient open-source AI Agent

A source-available, local-first alternative to Codex and Claude Code: an AI workspace for code, files, docs, websites, presentations, design, and video—with editable results and user-controlled tools.

A framework for agentic tool use training with reinforcement learning

CLI-first runtime for Codex, Claude Code, and AI agents to operate CAE solvers via plugins: COMSOL, Abaqus, Ansys.

600 行 TypeScript 写成的超级迷你版 pi，让你轻松从 0 写出属于你的 pi-agent

Agent behavior that compiles

Not only memory but a full story.

Review-first terminal diff viewer for agentic coders