#llm

One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

AI thinking indicators and a voice-agent orb for React Native and Expo. Six dotted loading animations plus an audio-reactive voice orb, on the UI thread with Skia + Reanimated. Port of Jakub Antalik's thinking-orbs.

The blood-brain barrier for autonomous agents. A context-aware LLM governance proxy that enforces credential starvation — identity-verified, provider-routed, cost-tracked, and audit-logged.

The governance layer LLM proxies promised as a TypeScript library you can read. Every call runs through one governed pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → schema-validated provider failover → usage log → LLM-judge No sidecar proxy to deploy.

Portable context memory across local agent tools. Discovers Claude Code, Codex, Devin, Copilot and OpenCode session stores and emits a context bundle you can load into any of them.

Anthropic provider plugin for OpenCode

Shared Go building blocks for psyb0t services: error sentinels, cache, DB, queues, rate limiting, a legacy Loki slog sink (superseded by github.com/psyb0t/slogging), Temporal, and LLM utilities.

High-performance LLM gateway in Go. 35x less RAM than Node.js version.

El repositorio no publica descripción.

A kinda close-enough xml for LLM

Parse, validate, and snapshot MCP servers. The swagger-parser for MCP.

Cache platform bridge for Symfony AI

Fnord is an AI code archaeologist.

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.

.gitignore for AI coding agents — tell Claude/Cursor what NOT to read

Axemere AI Gateway — TypeScript/Node.js SDK

Host-agnostic LLM agent execution on the OpenAI Agents SDK: model fallback, streaming, structured-output extraction, self-correction, and tracing — behind a small injected provider seam.

Harness layer of the Nexus funnel/harness split — Go library for one-turn model deliberation with provider abstraction

LLM-Friendly Convention Linter for AI Coding Tools

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

3,287 open-source icons for AI-era software — agents, MCP, RAG, LLMs — with an MCP server so your coding assistant picks real names. React, Vue, Svelte, Solid, Preact, React Native, Astro, Laravel, Flutter. MIT.

Budget-bounded LLM routing that finds the cheapest model and prompt meeting your accuracy target.

Agent SDK

Project VoidRift: Local-first Agentic Development Framework

MCP server exposing a SQLMesh project to LLM agents, model metadata, plans, column-level lineage, audits, environment diffs.

Failover proxy for LLM to automatically switch to best available model provider without interruption of your agents

Debugger CLI for AI agents — run, control, and inspect binaries programmatically with structured output for LLM tooling

TypeScript and JavaScript bindings for Cortext — npm package @augmem/cortext

Provider-agnostic Go AI framework for building RAG, agents, and AI-powered applications. Swap LLM providers without code changes — supports Ollama, OpenAI, and more.