llm-openai-via-codex - reuse a Codex subscription as an LLM backend
Simon Willison's plugin for the `llm` CLI that routes calls through an existing OpenAI Codex subscription. Lets you use Codex-tier models from any `llm`-aware tool.
All entriesGitHubToolFeatured GitHubTool GitHubTool GitHubTool GitHubLibrary GitHubTool GitHubTool GitHubTool GitHubHack GitHubLibrary GitHubLibrary GitHubLibrary
Tag
#llm
12 entries tagged with #llm.
AgentFM - SETI@home for local LLMs
Single Go binary that turns idle home GPUs into a peer-to-peer compute grid for LLM and AI workloads. Decentralized inference instead of renting from a cloud.
Lightport - OpenAI-compatible LLM gateway
Open-source AI gateway that makes any LLM provider OpenAI-compatible, originally a Portkey fork hardened around the MCP ecosystem at Glama.
otelite - local OTLP receiver for LLM dev
Single-binary Rust OpenTelemetry receiver and dashboard for local LLM development. Captures spans from agent runs without spinning up Jaeger or a vendor backend.
LLM-Rosetta - translate API calls between providers
Translator that maps OpenAI, Anthropic, and Gemini API requests through a shared intermediate representation, instead of writing N-by-M provider adapters by hand.
llm-ls - LSP server for LLM code completion
Hugging Face's language server that brings LLM-powered completion to any IDE that speaks LSP. Backends include llama.cpp, OpenAI-compatible APIs, and HF inference.
LLMFeeder - one-click web page to clean markdown
Browser extension that converts the current page to clean markdown and copies it to the clipboard for pasting into an LLM. Stripped of nav, ads, and chrome.
kimiflare - run Kimi on your Cloudflare account
Deploy Moonshot's open-weight Kimi model on a personal Cloudflare Workers account with no middleman API. Useful as a private OpenAI-compatible endpoint for agent harnesses.
tuicraft - TUI WoW chat client for LLM bots
Terminal client for the WoW 3.3.5a private-server protocol, designed to let LLMs inhabit and chat in-game. Currently chat-only, with plans for full game features.
AIMock - mock everything your AI app talks to
One package, one port, zero deps to fake LLM APIs, MCP servers, A2A, AG-UI, vector DBs, and search backends in tests.
M-flow - relevance-first agent memory
Memory layer for agents that surfaces relevant context instead of just similar embeddings. Episodic plus long-term memory backed by a knowledge graph.
any-llm - one interface for every LLM provider
Mozilla AI's unified Python client for OpenAI, Anthropic, Google, Mistral, and friends. Swap providers without rewriting a single call site.