Havuz

A step by step implementation to build an agent that runs for week to complete a task and self improve.

Evidence-backed growth decisions for AI-agent teams

Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses

Opinionated AI-native monorepo starter — build your MVP as a production-ready structure. apps/services/libs · Tilt · Nx boundary-enforced ·

Build UI apps with your AI assistant — together, live. An agent-native, cross-platform declarative-UI runtime in Go: describe UI as JSON, le

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff:

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. O

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

Open-source agentic infrastructure & alternative to Grok Bot. Bring Claude Code, Codex, OpenClaw or your own. Start without building from sc

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

This is the official catalog repository for AWS Quick. It contains curated, skills, plugins, agents, and integration configs that can be ins

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

Open-source, self-hosted personal travel app by Giovanni Brees - keep every flight, hotel, ride and trip on one living timeline. Built with

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted,

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

Lint rules for your AI agent's discipline, not its code

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve the

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, sa

ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-au

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers pe

A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate con

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

面向云服务器与 VPS 常驻部署的 Lark（飞书）Codex CLI 桥接器，同时支持本地运行；Lark (Feishu) Codex CLI Bridge for persistent deployment on cloud servers and VPS, with nat

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

Spec Kit writes WHAT. Superpowers enforces HOW. Thin handoff bridge for Codex and Claude Code.

Diagram→code through a deterministic rules gate: the AI proposes, 50 rules verify, only valid architecture lands. Try it: app.solarch.dev

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.

半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI s

The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned.

A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at th

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do li

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collis

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and

Unofficial CLI for automating Apple Feedback Assistant workflows: prepare, submit, attach, and verify

Agent-native long-term memory that learns after every run. File-native, auditable, and integrated with Pi, Hermes, OpenCode, and OpenClaw.

Serve clean Markdown from your Next.js site to AI agents, crawlers, and LLMs. Humans get HTML, agents get clean Markdown of the same pages.

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI,