slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It enables external applications to use AtomGit’s LLM models via the OpenAI standard interface, implements community-maintained signing, and provides secure token storage with a single‑binary deployment.
Who it is for
- Developers who want to use AtomGit Coding Plan models through OpenAI SDKs
- Self‑hosting enthusiasts managing multiple AtomGit accounts
- Researchers needing programmatic access to coding‑assistant LLMs
Use cases
- Calling models like deepseek‑v4‑flash from standard OpenAI clients
- Load‑balancing requests across several AtomGit accounts to avoid quota limits
- Auditing token usage and request latency via the built‑in dashboard
Strengths
- OpenAI‑compatible endpoints (`/v1/chat/completions`, streaming, etc.)
- Multi‑account round‑robin routing with automatic skip of disabled or exhausted accounts
- Single‑binary and Docker deployment with embedded React console
- Encrypted OAuth token storage (AES‑256‑GCM) and SHA‑256 API key digests
Considerations
- Requires a trusted network environment; no built‑in TLS and uses default weak admin password
- Unofficial community‑maintained signing implementation that may break on upstream changes
- Potential account restrictions or bans if used outside AtomGit terms of service
README quick start
Usage
Description
Expose AtomCode's CodingPlan AI models via a standard OpenAI‑compatible API.
Related repositories
Similar projects matched by category, topics, and programming language.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.