Havuz

LLM-native static vulnerability detection: point it at a repo and get a reviewable vuln report, the way a human auditor would.

Moved to PostHog/coherence — development continues there as @posthog/coherence.

Brain, agent, workflows, and docs. Local framework to automate your work.

A curated collection of skills for AI agents to properly work with datavault4dbt.

Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillat

High performance multithreaded task execution and optimization engine for agents and dweb apps

An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the com

An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine

Nirvana-OS engine: ready-to-run agentic operations. One sentence in, finished work out. Source-available engine for companies, squads and mi

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

Audit any agent decision across its past, present, and future, on one typed graph.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, a

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

CortexPrism — open-source AI agent operating system

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop

NEWTON: Agentic Planning for Physically Grounded Video Generation

Tutti, geliştiricilerin birden fazla coding agent'ı aynı dosya, görev ve bağlamı paylaşan bir çalışma alanında koordine etmesini sağlayan masaüstü uygulamasıdır.

Neden yükseliyor · Birden fazla coding agent kullanırken ortaya çıkan bağlam ve görev devri sorununa yönelik somut bir ürün öneriyor; 107 günde 3.786 yıldız ilgi gördüğünü gösteriyor. Ancak son 28 gündeki 3 commit ve tek farklı yazar, ilginin sürdürülebilir geliştirme faaliyetiyle aynı şey olmadığını düşündürüyor.

A full featured, powerful, and efficient AI Agentic Harness/Desktop Agent app designed from the ground up with local inference on consumer h

小说改短剧，从文本到视频的一站式 Agent 工作台。

An open-source desktop AI agent foundation powered by OpenCode and connected through OpenConnector, with local tools, permission controls, a

Autonomous multi-agent framework to optimize scientific software

基于多智能体（Multi-Agent）架构的 AI 投资分析平台，聚焦 A 股与港股市场，融合情绪面、技术面、资金面和基本面研究能力。 An AI-powered multi-agent investment analysis platform for China A-share

Kimi K2.7 Swarm Workstation — 300-agent parallel AI hive. Beats Claude Opus 4.8 on tool use (81.1% MCPMark), 5× cheaper. Win/Mac, one-click.

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segreg

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with determini

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

Agent-first patent-prosecution assistant — open, transparent, and yours. Drafts and redlines in your own Word files, on your own computer.

Proactive 5h usage guard for Claude Code (macOS). Pause before extra wallet on long batch/subagent runs. Account-level window visibility. /u

Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pic

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Loop Engineering, kodlama agent’larını bir repository’deki bakım ve geliştirme işleri için planlayıp denetlemeye yarayan pattern’ler, starter’lar ve CLI araçları sunar.

Neden yükseliyor · 110 günde 11.318 yıldız ve son 28 günde 68 commit ile 8 farklı yazar, belirgin ilgi ve yakın dönem geliştirme aktivitesi gösteriyor. Bu veriler benimsemenin veya etkinliğin başarısını tek başına kanıtlamaz; ilginin ne kadarının gerçek kullanıma dönüştüğü verilen bilgilerden bilinmiyor.

ASC is a super FAST and lightweight Android decompiler designed for Agents/Mobile Researchers.

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Autonomous software engineer. Researches, plans, builds, commits, fixes bugs, loops until done.

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Grix : Work with agents like talking to people.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Financial Services segment — Advisory Assistant orchestrator plus 12 specialist

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Higher Education segment — Campus Assistant orchestrator plus 16 specialist sub

Fast, offline code search and code intelligence for LLM agents.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Enterprise segment — Workplace Assistant orchestrator plus 12 specialist subage

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Legal segment — Firm Assistant orchestrator plus 12 specialist subagents.

CareerForge — AI job-search assistant inside Claude Code. /search ranks postings from your portals; /apply tailors a CV + cover letter (post

Taste-first club-music production that automates everything but the judgment. You direct in plain language; the agent writes each track's so

Your Hermes agents, one shared brain.

Enterprise-grade sovereign AI for organizations where SaaS AI isn’t an option.

Training-free agentic framework for analog circuit design automation: an LLM multi-agent system with self-evolving memory. KDD 2026 (AI4Scie

npm-compatible registry that crowdfunds supply chain security: donors pay auditors and maintainers in USDC on Algorand via x402

Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs