Search

Autonomous Solana agent — SAP tool discovery, Ace Data Cloud AI services, x402 payment workflows. Built for OOBE x Ace Data Cloud bounty.

Linux/X11 computer-use tools for AI agents — Pi, Claude Code, OpenCode, any MCP-aware client. AT-SPI + xdotool, ~1k LOC. Drop-in replacement for the macOS pi-computer-use.

A framework-agnostic, git-native standard for defining AI agents

Multi-agent LLM pipeline for long-form novel continuation · 多 Agent 长篇小说续写流水线，19 轮迭代 + 全程 mock-first

Lifecycle-shaped Claude Code agent kit: scheduled audits → ready-state issues → developer-agent PRs → multi-persona advisory review. Six named PR reviewers, five audit scanners, one installer. Claude-only by design.

A code-first framework for building deterministic CLI tools that LLM agents can discover, validate, and invoke with zero guesswork. Powered by Zod schemas and structured output contracts.

Minimalist toolkit to build the foundation of Agent harness.

🏛️ 通用型AI认知架构 · 诺亚三代二型 — 抽屉级联上下文管理 / 记忆闭环(Mnemosyne) / 自主进化。实战萃取，MIT开源

GlassHands is a computer-use agent framework

LLM-powered automation agents for multi-step task execution, decision-making, and workflow automation.

Deterministic context compression for LLM chat, RAG, and agent pipelines

AI Route Planning Agent — Spatial-RAG + TSP + Interactive CLI

LarkPal Agent SDK — 基于火山方舟的 AI Agent 引擎，实现 larkpal RuntimeAdapter 接口

Local CLI for discovering AI agent skills and detecting conflicts.

Framework-agnostic agent skill library. Drop-in skills for Claude Agent SDK, LangChain, OpenAI Assistants, CrewAI, AutoGen, and any AI agent runtime.

Verified AI development. Scan your project, generate context, verify every change through a four-agent pipeline.

Business knowledge primitive for AI agents

Core mission, directive, artifact, and schema utilities for keel-agent.

In-memory Git for AI agents, slow filesystems (EFS/NFS), and test harnesses. Bash-like exec() dispatcher, no subprocess, isolated per-instance volumes, .gitignore-aware loading, explicit flush.

Deterministic contract layer between humans and coding agents. Drop into any repo to make AI agents (Claude, Codex, Copilot, etc.) operate under explicit, enforceable rules.