A

anthropic

A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.

GitHub: https://github.com/ultralytics/lite

https://github.com/ultralytics/lite/releases/latest

Shell wrapper for OpenAI's ChatGPT, Whisper, and TTS. Features LocalAI, Ollama, Gemini, Anthropic, and more.

LLM token stream viewer: see per-token confidence and perplexity from OpenAI or Anthropic logprobs, and rewrite every other token live. CLI and web UI; mock mode runs locally with no API key. Rust.

Command-line benchmark for LLM APIs: send the same prompts to OpenAI and Anthropic models concurrently and compare p50/p99 latency, tokens per second, cost per request and success rate. Rust.

Single-header C++17 libraries for LLM features: OpenAI and Anthropic streaming, retries, caching, cost estimates, RAG, structured JSON output and tool-calling agents. Copy one .hpp, no SDK, no package manager.

Tokio-native async LLM client for OpenAI and Anthropic with retry, circuit breaker, streaming, budget enforcement and tracing. Rust.

Single-header C++17: stream OpenAI and Anthropic chat responses token by token over SSE. Part of llm-cpp.

🛒 AI chat & product/category summaries in Amazon shopping, powered by the latest LLMs

A brief-to-build engine for Notion. Claude drafts the spec, an automated gate checks it, and a blocking question stops the pipeline instead of being answered by invention.

Run Claude Code in a Sublime Text panel with live highlighting of the files it edits, plus optional rsync-over-SSH project sync.

A Go engine for talking to LLMs that doesn't give a shit which one. Streaming, tool loops, history that actually fits the context window, retries that don't repeat themselves, and typed structured output. Swap OpenAI for Anthropic by changing one line. Library, not a framework — you own the loop.

Self-hosted AI chat that deploys as one Go binary. Streaming SSE, OpenAI and Anthropic upstreams, MCP tools, and generative UI that renders live charts and components from model output. Postgres or SQLite.

PromptCape — Java code obfuscation proxy for AI coding assistants (Claude Code, Cursor, Mistral). Docs, examples, FAQ. Documentation, technical articles, and Java framework examples for PromptCape — a Java code obfuscation proxy for AI coding assistants.

Mobile AI usage and quota dashboard for developers. Santoken helps track ChatGPT/Codex, Claude/Anthropic, and Google AI/Antigravity accounts in one Android app: remaining quota, plan tiers, model limits, reset times, refresh status, and release builds.

Working notes for pointing the Anthropic Go SDK at an Anthropic-compatible gateway through ANTHROPIC_BASE_URL (Antigravity proxy), plus the glab CLI issue-and-branch workflow shared across these agent projects. Specification and prompts only - no implementation committed yet.

MCP server: current per-million-token rates for 69 LLMs and the cost math

A self-improvement flywheel for Claude Code — 4 layers that turn ephemeral sessions into compounding, durable learning.

A skill for AI coding agents that scaffolds a safe, multi-model chatbot for Telegram or Discord. Supports Claude, GPT, Gemini, and OpenAI-compatible backends. Nine safety layers on by default. Named for R. Daneel Olivaw from Asimov.

Multi-source RAG pipeline with hybrid vector + keyword retrieval, LLM-powered concept knowledge graph, adaptive search weighting, and evaluation framework.