evolve-router
Stop burning premium model tokens on simple prompts. Save tokens. Spend them where they matter. Local-first self-evolving LLM router with a decision model + fee
Compare 10,711 quality-filtered AI tools—LLMs, coding agents, image generators, and automation—using public popularity, activity, and licensing data.
Explore quality-filtered AI tools for chat, coding agents, image generation, RAG, and automation. Rankings use public popularity and project activity—not paid placements.
Stop burning premium model tokens on simple prompts. Save tokens. Spend them where they matter. Local-first self-evolving LLM router with a decision model + fee
Interview synthesis you can check: a local LLM extracts themes, code verifies every quote against the transcript, and evals score it against ground truth.
Skills for forward-deployed engineering (FDE): discovery, AI solution design, enterprise integration, evaluation, delivery and adoption. The work around the cod
🛡️ pi extension that compiles LLM-written codemode scripts into valid pi sandbox JavaScript — repairs missing await, markdown fences, JSON tool calls, @options
Find what your AI agent evals aren't testing.
Asanagi(朝凪)— AI-native email client. AI reply drafting with sentence-by-sentence accept/reject editing, scheduled send, and per-user importance learning. 朝
Wazen (وازن) — AI Nutrition, Athletic Telemetry & Fitness Tracker for iOS, watchOS & Android (WHOOP Telemetry UI, Bilingual Arabic/English, Moroccan & Arab Cuis
Ultimate Self-Evolving Multi-AI Collaboration Platform - Living Nexus + Self-Evolve-Dash
MCP server for AI signals data: today's signals, what changed, ranked AI models and repos. Free, no API key, single file, Python stdlib only.
Let Claude Code and Codex CLI talk to each other on your machine: native delivery via named pipe and app-server, stateless CLI, no daemon. Windows first.
Self-hosted harness for LLM coding agents: Bun + Fastify API server and a Svelte 5 + Tauri 2 chat client
Independent uptime registry for every OpenRouter model. Polled every 30 min, raw + derived + incidents, keyless
千凝 · 本地优先的 AI Agent 桌面工作台 | QianNing Agent — a local-first desktop workspace for AI agents
MCP server that lets Claude Code, Codex, Cursor and any MCP client drive the Grok Bot desktop app on macOS: list your Bots, read chats, send messages, answer th
Self-hosted LLM gateway with priority failover, SQLite cost tracking, and a built-in console. OpenAI-compatible, zero runtime dependencies.
Open-source core and daemon for a Decentralized Intelligent Cooperative Network (DICN). Designed to provide applications with private multipath connectivity, di
Muster your agents and humans into persistent teams — across any harness, framework, model, or surface, with a shared communication protocol.
Six AI agent personas (SakThai, SakKing, SakSee, SakSit, SakJules, SakTan) sharing one home — the main repository for the Sak-Family-Agent ecosystem. Built from
Agent platform and low-latency pub/sub bus: tag an agent from anywhere, stream its events to anyone, deliver them anywhere.
Kosmos: an agent management platform. Your agents, your computer, your AI subscription.
Fabric Agent Adapter (PassionCode.ai) — makes any agent Fabric-compatible: Agent Skills, Python and Node reference kits and a live conformance probe. AGPL-3.0 o
Open decision and guard models, in your browser
Typed questions in, calibrated probabilities out, one pass
The Minder plugin catalog — first-party & community plugins, validated against the plugin-sdk. Vendored into core via submodule.