Havuz

Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own Ope

Pilly - AI trading copilot for Solana memecoins. Live trending, crew verdicts, charts, price alerts, PnL tracking and a desktop pet that rea

Open-source Fugu: the open-source LLM orchestration brain.

Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you o

High-performance bridge proxy connecting Claude Code CLI & Anthropic SDK to ANY OpenAI-compatible LLM provider (DeepSeek, OpenRouter, Groq,

Local-first Electron cockpit for the Codex SDK, OpenRouter, multi-agent crews, and bounded computer access.

An AI teammate for Slack and Microsoft Teams that runs on open-weight models through any OpenAI-compatible endpoint. One Go binary with an a

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

Terminal coding agent with browser UI, MCP, Obsidian memory, and live office floor. Any model via OpenRouter. MIT.

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.

Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append

A standalone, personality-driven multi-agent workspace application written in C, & C++

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

Open-source native Apple client for the AI you choose - iPhone, iPad, Mac, Apple Watch, and CarPlay. Your keys; no intermediary.

⚖️ TecJustiça PJe — extensão gratuita para o Chrome que ajuda a ler, analisar e organizar os processos do PJe: chat com IA sobre os autos (s

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP

Gray is an open-source (MIT) AI agent harness shipped as one static Rust binary. Bash-only tools, resumable JSONL sessions, a self-compactin

Natural-language end-to-end tests for web apps, powered by Jev and Playwright.

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

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

Autonomous AI agent for Instagram — generates reels, carousels, memes, quote cards and posts them on autopilot. Free-tier LLM router, commer

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover,

MCP server that turns the pi coding agent into a steerable background worker: delegate a task, redirect it mid-run, and keep its context out

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

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

Speak into any Android app — and have it write in another language. A dictation orb that appears only when a text field has focus, cleans up

One free AI endpoint, every free tier behind it. Local OpenAI-compatible gateway routing across OpenRouter, Groq, NVIDIA NIM, Cloudflare Wor

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

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qw

Practice English where you write it: realistic email, Slack, GitHub, and chat rooms with an AI persona and a coach on every message. BYOK: r

A TypeScript proxy that intercepts Antigravity's Gemini API and routes to NVIDIA or OpenRouter — chat, tools, browser automation, all worki

SEPCC — A Claude Code proxy with context that survives. Route Claude Code through 17+ providers, resume sessions across restarts, and never

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work togethe

Free AI code reviews on every pull request. Bring your own key (OpenRouter free tier works), runs in your repo as a GitHub Action - no quota

Reformat a live LLM token stream inflight — separate thinking from answer, collapse repetition, normalize. Google Vertex / OpenRouter / meta

Vitreon - The Ultimate Multi-Agent AI Orchestration Platform built with Next.js, Tailwind CSS, and AI SDK.

OpenRouter TypeScript harness for reproducible LLM benchmarks and evaluations.

Discontinued. Succeeded by OpenCognit Desktop — every coding agent in one window → opencognitos.github.io

An AI assistant whose memory belongs to you. Local-first Mac app, plain markdown workspace, bring your own model.

Enterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-t

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully

Tailor your resume and cover letter to a job posting, inside Chrome. No account, no server - bring your own AI provider key.

LLM spend tracking and budgets for Rails — by user, feature, or any tag, in your own database, no proxy.

Android AI agent app. Kotlin + Rust via UniFFI.

Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

Agent harness research ebook — model-agnostic architecture specification (June 2026)

One-click knowledge system for documents, internal bots, and AI agents

Autonomous YouTube AI agent: LLM script, TTS voice, stock clips, FFmpeg editing, AI thumbnail, auto-upload — 100% free, Telegram-controlled.

Automate a WeChat group's daily work-report roll-call — start, chase non-submitters, and LLM-summarize for the manager. wxauto + FastAPI + h