Minimal Rust SDK port of LiteLLM – unified interface for chat, embeddings, images, and video across OpenAI-compatible, Anthropic, Gemini, and xAI providers
Build LLM clients with ease, attach them to your tools
High-performance embeddings client for multiple providers
Analyze Claude Code usage data from local JSONL files
LLM provider integrations for agent-diva
Generic OpenAI-compatible Chat Completions client for chat-rs. Bring your own server (Ollama, vLLM, llama.cpp, LiteLLM, etc.).
LiteLLM proxy provider for atomr-infer — implements ModelRunner against the LiteLLM unified API gateway, fronting OpenAI-compatible endpoints for any provider LiteLLM supports.
LiteLLM proxy provider for rakka-inference — implements ModelRunner against the LiteLLM unified API gateway, fronting OpenAI-compatible endpoints for any provider LiteLLM supports.
Personal developer-companion CLI: scans your repos, indexes code semantically, watches your activity, and moves AI-agent sessions between tools (Claude Code, Aider, Goose, OpenAI Codex CLI, Continue.dev, OpenCode).
Provider and model catalog for anyllm-proxy
Harmony-aligned, OpenAI-compatible agent orchestration in Rust with tools, realtime, and voice.
Remote-provider infrastructure for atomr-infer — distributed rate limiter (CRDT), circuit breaker, retry/backoff, SSE parser, session lifecycle.
No description provided.
No description provided.
No description provided.