Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A small, powerful, open-source CLI coding agent that works with open models.
| Date | Stars |
|---|---|
| 2026-07-31 | 309 |
| 2026-08-05 | 312 |
| 2026-08-06 | 312 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
 # Swival A coding agent for any model. [Documentation](https://swival.dev/) Swival is a CLI coding agent built to be practical, reliable, and easy to use. It works with frontier models, but its main goal is to be as reliable as possible with smaller models, including local ones. It is designed from the ground up to handle tight context windows and limited resources without falling apart. It connects to [LM Studio](https://lmstudio.ai/), [llama.cpp](https://github.com/ggml-org/llama.cpp), [HuggingFace Inference API](https://huggingface.co/inference-api), [OpenRouter](https://openrouter.ai/), [Google Gemini](https://ai.google.dev/), [Gemini Enterprise Agent Platform](https://cloud.google.com/vertex-ai) (formerly Vertex AI), [ChatGPT Plus/Pro](https://chatgpt.com/), [AWS Bedrock](https://aws.amazon.com/bedrock/), Apple Foundation Models (experimental), any OpenAI-compatible server (ollama, mlx_lm.server, vLLM, etc.), or any external command (`codex exec`, custom wrappers, etc.), sends your task, and runs an autonomous tool loop until it produces an answer. With LM Studio and llama.cpp it auto-discovers your loaded model, so there's nothing to configure. Pure Python, no framework. ## Quickstart Pick the provider that matches how you want to run models: | Provider | Auth | Required flags | First command | | ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------- | | LM Studio | none | none | `swival "Refactor src/api.py"` | | llama.cpp | none | `--provider llamacpp` | `swival --provider llamacpp "Refactor src/api.py"` | | HuggingFace | `HF_TOKEN` or `--api-key` | `--provider huggingface --model ORG/MODEL` | `swival --provider huggingface --model zai-org/GLM-5.2 "task"` | | OpenRouter | `OPENROUTER_API_KEY` or `--api-key` | `--provider openrouter --model MODEL` | `swival --provider openrouter --model z-ai/glm-5.2 "task"` | | Google Gemini | `GEMINI_API_KEY`, `OPENAI_API_KEY`, or `--api-key` | `--provider google --model MODEL` | `swival --provider google --model gemini-2.5-flash "task"` | | GEAP (Vertex AI) | Google Cloud ADC or `GOOGLE_APPLICATION_CREDENTIALS` | `--provider geap --gcp-project ID --location REGION --model MODEL` | `swival --provider geap --gcp-project my-proj --location us-central1 --model gemini-3.1-pro "task"` | | ChatGPT Plus/Pro | browser auth on first run or `CHATGPT_API_KEY` | `--provider chatgpt --model MODEL` | `swival --provider chatgpt --model gpt-5.5 "task"` | | Generic | optional `OPENAI_API_KEY` | `--provider generic --base-url URL --model MODEL` | `swival --provider generic --base-url http://127.0.0.1:8080 --model my-model "task"` | | Apple FM (exp.) | none (local server) | `--provider applefm` | `swival --provider applefm "task"`
Excerpt of 19,038 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:00249019785e8c0b, llm:Repository topics and description: topics include agent, agent-to-agent, ai, cli, code, coding, eval, huggingface, lmstudio; description: 'A small, powerful, open-source CLI coding agent that works with open models.'
matched fp:00249019785e8c0b, llm:Repository topics and description: topics include agent, agent-to-agent, ai, cli, code, coding, eval, huggingface, lmstudio; description: 'A small, powerful, open-source CLI coding agent that works with open models.'
matched fp:00249019785e8c0b, llm:Repository topics and description: topics include agent, agent-to-agent, ai, cli, code, coding, eval, huggingface, lmstudio; description: 'A small, powerful, open-source CLI coding agent that works with open models.'