|
ShareQuota — free local AI router for Claude Code & Codex
A free, MIT-licensed AI router that runs on your machine: Claude, ChatGPT, Gemini, DeepSeek and OpenRouter behind one endpoint and one key, with auto-failover.
|
82 % |
|
Klenny Code — The open-source AI coding agent for your desktop
Klenny Code is a free, open-source desktop coding agent. Bring your own OpenRouter key and use hundreds of AI models, with memory, cross-project lookup, sche...
|
81 % |
|
Kiwano — Local-first AI Provider Manager
Discover, compare and switch AI providers locally. Connect Claude Code, Codex and Grok Build to a local gateway in one click — nothing leaves your machine.
|
81 % |
|
GopherMind — an AI coding agent that asks first
A single Go binary that turns your own OpenAI-compatible model into a terminal coding agent. Local llama.cpp, Ollama, LM Studio, vLLM or hosted. Every mutati...
|
80 % |
|
WhyCodes · The AI coding agent
WhyCodes is an AI coding agent for your terminal, IDE, or desktop. Connect any model you already use.
|
80 % |
|
OpenModel — Multi-Model LLM API Gateway
OpenModel is a hosted multi-model LLM API gateway. One API key for any model, with routing, retries, logs, and billing in one layer.
|
80 % |
|
Revet — See what your diff really changes
Code review CLI with cross-file impact analysis, ML pipeline checks, and optional AI reasoning. Not another GPT wrapper.
|
80 % |
|
Kadegate — Kadegate
One OpenAI-compatible endpoint. Access top open models with a single API key.
|
80 % |
|
Quell — Find untested edge cases in your Python code
Quell finds untested edge cases in Python codebases — docstrings, Pydantic models, guard clauses. Three-bucket output: WRITTEN, SCAFFOLDED, FLAGGED. 5-gate p...
|
80 % |
|
Glass Slipper · The one-click hybrid LLM solution
Glass Slipper routes your AI coding tasks between frontier and local models automatically. Work in Claude, Codex, or Cursor. Heavy thinking goes to the cloud...
|
80 % |
|
Specific Code | Free Coding Agent for Your Terminal
Specific Code is a free, terminal-first coding agent. It reads your repo, writes patches, runs your checks, and works with Claude, GPT-5.1, Gemini 3, DeepSee...
|
80 % |
|
NautGate — prove which model actually answered
An open-source, memory-aware LLM gateway. Route Claude Code, Codex, Pi or your own app to any model — and get a provable record of which model really served...
|
80 % |
|
Codex Router: DeepSeek, Kimi, GLM, Claude & Copilot
Free and open-source on GitHub: Codex Router adds DeepSeek, Kimi, GLM, Grok, Claude and GitHub Copilot models to Codex App and CLI. Install and troubleshoot...
|
80 % |
|
Bridge1 — local models that don't slow down your coding agent
|
80 % |
|
RunJam — One Desktop. All Your AI Agents. Zero Lock-in.
A local-first desktop manager for Claude Code, Codex CLI and Gemini CLI. Install once, run any model on any agent, and manage every project in a single window.
|
80 % |
|
Neely Inferred
Rob Neely builds small, self-contained tools — GPU visualizers, offline data pipelines, and the occasional web app. All of it free to take.
|
80 % |
|
LM Warden: self-hosted LLM gateway for your own GPUs
Serve LLMs from your own NVIDIA GPUs with vLLM and llama.cpp: one OpenAI-compatible /v1 endpoint, a key per app, and readings per card.
|
80 % |
|
Fix Your AI-Built App: Rescue & Security Audits | LivePCTech
Broken, stuck or insecure app built with Lovable, Bolt, Replit or Cursor? A senior engineer diagnoses and fixes it in your existing code. $300 triage, fixed-...
|
79 % |
|
InSitue — Point at the bug, get the fix
Drop one snippet into your deployed app. When someone points at something broken, InSitue clones your repo into an ephemeral microVM, fixes it with an AI age...
|
79 % |
|
Modelwing — One API for every model
An OpenAI-compatible gateway to curated LLMs with prepaid credits and transparent pricing.
|
79 % |
Detected social media networks