#llm

Loom is a high-performance, graph-based AI workflow engine for Go. It allows you to build complex agentic systems by defining multi-step workflows as directed graphs, seamlessly connecting them to any large language model, and persisting execution state for long-running or interrupted tasks.

The state layer for LLM agents: durable conversations, agent-curated memory, skills, a shared board and a ledger of who did what — on storage you own.

An open registry for discovering, verifying, and trusting AI agents.

AI for the Command Line

Read almost any file as Markdown for AI agents and LLM apps. 150+ formats, pure TypeScript — PDF, Office, iWork, HWP, email, ebooks, archives, and more.

Rust interfaces to the streaming code protocols.

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

Compose agents into a graph over oneharness/onejudge and merge their outputs into one event stream.

DeepSeek API SDK for .NET developer

Reusable Go runtime packages for building and configuring ACP-backed agents

Self-hosted error-monitoring for Python pipelines: capture exceptions, deduplicate, diagnose root causes with LLMs, route alerts (Telegram/Slack/email/GitHub/S3), and auto-generate fix PRs — from a logging handler or one report() call.

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

An auditing engine for code you did not write. certify plants faults and runs YOUR suite against each one; review hands the code to a cold agent that must prove every claim with a script corral runs. Each verdict is a signed, hash-linked entry on a git branch any DuckDB queries straight off GitHub.

Memory and knowledge service, MCP and TUI for AI agent workflows.

Lightweight Go workflow graph runtime for building, running, and serving AI agent workflows with LLMs, tools, routing, schedules and webhooks.

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.

Blazor components for tailwind

CLI tool to export and analyze workout data from the Liftoff fitness app — workouts, exercise stats, bodyweight trends

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

Nucleo Agentic Runtime

Semantic code search for coding agents — search by meaning like grep, trace call graphs, find tests & blast radius. 100% local embeddings (ONNX/MLX), MCP server, plugins for Claude Code, OpenCode, Codex & Droid.

🤖 Faker provider for generating AI/ML fake data - models, companies, frameworks, datasets

Math Calculator MCP Server

Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐，由你自己的 Agent 驱动投资研究。基于开源的 Codex Harness 打造。

PHP LLM client with support for cache, tools and async requests

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

DeepSeek platform bridge for Symfony AI

Google Gemini platform bridge for Symfony AI

Generic platform bridge for Symfony AI

Mistral platform bridge for Symfony AI