Havuz

A lightweight dashboard and reporting tool powered by OmniRoute - The Free AI Gateway

CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B LLM

Turn a GitHub repository or Hugging Face model into a finished vertical reel: video, cover art and per-platform copy.

The open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic

Talk to anyone: /coach persona plugin for Claude Code — research any public figure from their YouTube + web, then talk to them

Fast Gemma 4 inference in pure Java

Add a talking 3D AI avatar to any web app. Samples and tools for the Perxona Connect SDK: <sv-presenter> web component, lip-sync, text-to-sp

LLM-managed personal knowledge base. Auto-extracts from git repos, Claude Code sessions (via ccrider FTS5), and iMessage bookmarks. Cross-pr

Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

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

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewe

Strands-based agents and harnesses for agentic benchmarks.

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

MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.

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

Personal AI OS for Entrepreneurs. Ultimate OpenClaw setup in minutes. Experience frictionless flow states in your daily workspace — your AI

A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs

Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.

The source-available AI agent operating system

小liu破甲 - Codex CLI jailbreak prompt and one-click deploy tool. 基于CTF框架的Codex破甲提示词与一键部署工具

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

Free, open-source desktop app to run Claude Code, Codex, Cursor CLI and Antigravity agents in parallel with git worktrees and diff review.

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

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

Open WebUI tool port of Superpowers by Jesse Vincent — brainstorm → spec → plan → execute agentic dev workflow for local LLMs

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

Never hit rate limits again. One OpenAI-compatible endpoint for 60+ providers & 1,200+ models — smart auto-fallback, prompt compression, 60-

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Lightweight agent multiplexer, all in one Web dashboard

Agent skills that help you publish in the AER faster — identification-first empirics, AEA-compliant replication, Keith-Head intros, R&R rebu

An LLM-friendly, single-binary, drop-in replacement to Supabase

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

Open-source, self-hostable, always-on personal agent with its own computer. Runs on Cloudflare Workers or Node.

本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。

Code for DrivingBench: AI models drive real cars (comma/openpilot, Toyota and Tesla) through MCP tools, a runner loop for API models and tra

Open-source platform for creating, distributing and running sovereign EU-compliant LLMs. Verticalize any model for your domain, language and

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

⚔️ Compare AI models side by side — same prompt, streamed answers, live code previews, speed, tokens and cost. Keys never leave your browser

Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of read

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

An open source, Native AI Gateway and LLM proxy built in Rust

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.