Havuz

Run-aware token governance for multi-agent systems.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

The open startup repo — everything a founder needs to start and run a company in the agentic era: the comprehensive founder processes from a

Verifiable multi-agent patch evaluation infrastructure

Unified Harness TUI (ACP client). Self-Improvement TUI plugin of DeepSeek Harness. Everything Here Is Also A Plugin.

The official FastMCP TypeScript library for building MCP servers, clients, and apps 🏎️ 🏎️ 🏎️

ACP adapter for ZCode — drive GLM-5.3 and GLM-5.3-Flash from IDEA, VS Code, Zed or any ACP client; pair with zcode-acp-remote for phone/web

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts)

Tu asistente personal, directamente en tu ordenador. Habla contigo por voz, gestiona WhatsApp, atiende llamadas, consulta la web y recuerda

A composable framework for reproducible evaluation of long-running agents.

The factory for custom internal software, purpose-built for human2agent work.

Build a coding agent from scratch, one harness primitive at a time. 15 chapters (ch-00..ch-14), each green on two gates.

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes.

One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

A mysterious multi-agent swarm framework summoned by TAW Agent from 1971 to help you craft a better future towards 2133 & beyond. Ankh.md is

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

Agentic event-venue operator demo built on MongoDB Atlas. Showcases three-layer memory (long-term, short-term, shared), hybrid retrieval wit

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

基于 Go 与 Eino 的多模态视频解读 Agent：阅读转写文本/字幕、按需查看真实画面，将 B站和 YouTube 视频整理为图文文章，支持围绕原视频持续问答。

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

Turn Claude Code into a senior software architect that orchestrates a team of specialist agents and audits itself. An 8-phase skill with TDD

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard /

CliffCompaction — autocompaction for long-horizon coding agents

Self-hosted web viewer for Claude Code session transcripts — read, search, replay, and audit every session you have ever run

Effect building blocks for agentic ai

Hermes Agent context engine: the main model writes the compaction handoff on its cached prompt prefix

Self-host your own AI app builder: FOSS v0/Lovable like.

Agent-first lightweight browser automation — direct CDP, no Playwright, more accurate and more reliable.

A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persi

AI compiles hallucinated code that pass. This fixes it before accepting it. 100% Deterministic

A harness for embodied intelligence — connecting agents, robot skills and the physical world through execution, feedback and recovery.

An agent buddy that can run on an ESP32 device or on your desktop!

Desktop automation CLI for AI agents. Fast native Rust CLI.

Keep your skills sharp. Intelligence for agent context.

Transcript analysis for long-horizon agent evaluations

Prove your agent skills work before you ship them.

An agent-native runtime for embedded devices, powered by PocketJS. Build installable, updatable JavaScript apps for people and agents.

A persistent workspace for development work.

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case s

Human in the loop for agent workflows

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

a unix-like du command line tool to count token usage per files and directories

"Multi-Agent Team — 让31位导演大师成为你的AI创作团队"

最终的 MCP | Terminus MCP

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.