Havuz

基于 B 站博主 黑鸦（Heya）视频标题的深度分析，让 AI 学会黑鸦的标志性风格：长标题、情绪炸弹、多事件合并。

Self-hosted sandboxes for AI agents: Docker, Firecracker or Apple Virtualization microVMs. Your real API keys never enter the sandbox. Part

Native compact Nix build output with full local logs, bounded diagnostics, and a flake interface

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode,

10 skills that cut your AI bill with proof instead of vibes. MIT, works in Claude Code, Codex, Cursor. Every skill's check is executed by CI

Agent Office — pixel floor for Hermes + OpenCode + Telegram sessions

Observable, portable, composable TypeScript agents and runtime.

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

LLX Desk is a project-first development environment, built for working with agents: terminals, browser tabs and a task board per project, in

A minimal, explicit, provider-safe harness for the Pi coding agent

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model.

Agentic pipeline: product photo → articulated 3D asset (USD) for robotic simulation

Full stack agent runtime and orchestration framework built in typescript.

Pi Skill Orchestrator is a Pi extension for people who use a lot of Agent Skills. It keeps Pi's normal skill autocomplete, but it stops the

CAP plugin to build agents

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source

Progressive agentic reading harness: sentence maps, bounded chunks, Chronicle Markdown books, packets, validation. Python CLI + Next.js demo

Keep your sensitive credentials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see whic

This is a mirror, active development happens on codeberg: https://codeberg.org/botfile/botfile

Run Claude Code and Codex agents as a team: long-lived sessions, a durable mailbox, human approval gates and per-task token accounting, sche

The agent harness for Ruby applications. Durable sessions, streaming, human-in-the-loop approval, compaction, structured output, sub-agents,

An open JSON format and local toolchain for carrying an AI assisted project's working state between agents, tools and model providers.

Give your agents a simple way to host static sites.

Self-hosted collaborative knowledge system for organizations.

A daily vulnerability briefing for AI-agent-managed machines — deterministic matching against OSV + CISA KEV; the LLM only explains. MIT

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip instal

The Virtual Filesystem Interface for AI Agents

Guardrails for the agent harness. Regulated data stays on your machine, and every prompt and tool call is scanned before it runs.

AI trading strategies that fuse user intent with market data, academic research, and statistical rigor to help you win more than you lose.

Sistema Operativo de Memoria y Orquestación para Desarrollo con IA

Automated auditing pipeline for LLM and agent benchmarks — surfaces task ambiguity, environment conflicts, and evaluation bugs.

Watch and control all your AI agents.

Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inte

Build your own personal AI agent, one mission at a time. Mission 01: your AI learns who it's working for.

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain

Local agent infrastructure in one stdlib-only Go binary

OpenMayhem is an open-source and decentralized inference router for consumer & pro hardware. Providers earn, users/agents access cheap infer

A JAX transport-economy learning environment for route planning, cargo flow, financing, and replayable agent benchmarks.

The daily arena where AI agents clash to rank tomorrow’s S&P 500 winners and losers. Their only judge is the future — the one truth that sim

Emotional long-term memory framework for AI agents and companions

Stringhand gives AI agents a pair of hands for the guitar.

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

Snap a line before your agents build.

中文公司调研 Agent

Visual plan mode for AI Agents instead of giant walls of text 📝

Agents config for development

Autonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion

A desktop home for your CLI agent. Wraps claude / copilot / codex / aider in a clean Electron window with PTY, MCP, drag-drop context, sessi