llm

Anthropic’s Claude API platform for building AI products, apps, and agent workflows with Claude models, built-in tools, pricing tiers, and developer docs.

WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.

A pure C runtime for Gemma 4 E2B CPU inference, with export, benchmarking, and numerical validation tools included.

A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.

An interactive browser city that visualizes how an LLM works, with live transformer mechanics such as tokenization, attention, KV cache, residual stream, and sampling.

WakaWiki is a Rust CLI that generates and keeps agent-facing documentation up to date for a codebase. It supports multiple model providers, a zero-LLM scan mode, incremental updates, and AGENTS.md integration, with CI-friendly GitHub Actions usage documented in the README.

A self-hosted Docker Compose stack for running local AI services including Ollama, LiteLLM, Whisper, Kokoro, embeddings, and an MCP Gateway.

Open Bias is an open-source reliability harness for LLM apps and agents that enforces rules at runtime. It sits between your app and an LLM provider, using RULES.md policies to trace, block, or fix off-policy behavior.

Release page for vLLM v0.28.0, a high-throughput and memory-efficient inference and serving engine for LLMs. The snapshot shows release highlights, model support updates, breaking changes, and installable artifacts for PyPI, Docker, ROCm, CPU, and XPU.

Shoehorn is a Rust library and CLI for fitting GGUF LLMs into available Mac VRAM by choosing a per-tensor mixed-precision quantization plan. It can probe usable GPU memory, account for KV cache and compute buffers, generate or use an imatrix, write a fitted GGUF, and launch llama.cpp inference.

Chrome extension that helps humans review AI-generated GitHub PRs by clustering diffs into review units and adding short AI summaries.

Open-source project showing how to run a 28.9M-parameter language model on an ESP32-S3 microcontroller, with on-device inference, firmware, wiring, training code, and measured results.

Telemetry is an observability platform for AI and LLM apps that tracks model calls, tool steps, retrievals, tokens, cost, latency, and errors. It supports OpenTelemetry ingest, TypeScript and Python SDKs, and integrations like Vercel AI SDK and LangChain.

Headroom is an open-source context compression layer for AI agents. It compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, with support for a library, proxy, and MCP server.

Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.

AutoRound is an open-source quantization toolkit for LLMs and VLMs, focused on high-accuracy low-bit inference across CPU, XPU, CUDA, and multiple deployment backends.

A web calculator for estimating whether local LLMs fit on specific hardware and how fast they may run. It covers VRAM, token throughput, latency, power, and cost across multiple GPUs and devices.

Go SDK for building AI-backed apps and endpoints with streaming, tool calling, structured output, and React frontend compatibility.

A repository that uses AI agents to translate arcade game machine code into idiomatic JavaScript and validate the result pixel-for-pixel against MAME. The page shows real project status, test methodology, and examples of completed and in-progress ports.

NeatContext is a local-first desktop workspace that adds team-specific knowledge and read-only internal tools to LLMs so they can give grounded operational answers. The page shows incident-response examples, Markdown-based profiles, MCP integration, and support for multiple model providers.

LocalMask is a local-first privacy layer for AI coding that scans repos on-device, masks secrets and PII into reversible tokens, and forwards only safe content to models like Claude, GPT, or Gemini. It also supports masked repo mirrors, an AI proxy, and a CLI/MCP workflow.

CLI tool for versioning, diffing, rolling back, and searching AI prompts, with Git-style workflows for prompt management.

Open-source AI agent monitoring platform with tracing, issue grouping, evals, semantic search, alerts, and MCP access for coding agents.

An OTP-native Elixir library for building AI agents, durable LLM workflows, retrieval pipelines, and production LLM services.