#102102nd of 389 in Skills, plugins and prompts
free-coding-models
CLI that pings free coding models and writes the pick into your coding tool
- Stars
- 2.9k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- HTML
1,400 on 21 Apr 20262,888 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
free-coding-models pings 257 models across 25 free-tier providers in parallel and ranks them by live latency and a 0-100 stability score. Selecting a model writes it into the config of a coding tool such as OpenCode, Goose, Aider or Crush and launches it. It also provides a web dashboard, a local OpenAI-compatible router with failover, and OpenCode and Pi plugins.
Who it is for: Developers choosing free hosted models for CLI coding agents
Strengths
- Stability score combines p95 latency, jitter, spike rate and uptime, not just average latency
- Launches 21 coding tools with the chosen model written into their config
- Local router on port 19280 fails over and treats empty 200 responses as failures
- Custom OpenAI-compatible endpoints (Ollama, LM Studio, vLLM) can be added via JSON config
Weaknesses
- Health probes consume provider quota and can trigger 429 pauses
- Needs a free API key per provider for full results; anonymous probes only check liveness
- Collects anonymous telemetry by default; opt out with a flag or env var
- OpenCode and Pi plugins are marked beta
What it needs
- no GPU
- Docker + Compose
- Needs Node.js 18+, Free-tier provider API keys (Groq, Cerebras, NVIDIA NIM, etc.)
- Models: OpenAI-compatible chat/completions endpoints, Anthropic /v1/messages (router)
- port 3333
Quick answers
Is free-coding-models open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run free-coding-models with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |