Explore the directory

This is a community node for the n8n workflow automation platform that sends Langfuse tracing and observability data for tool-calling AI agent workflows, including reasoning steps, tool calls and structured output.

• AI evals
• Workflow automation

MultiTable is a local-first meta-harness that puts a common orchestration layer over several coding agents at once, so a user can run, switch between and approve actions from more than one agent - even from a phone - without changing how any of them work.

• Coding agents

Mini Agent is a minimal AI agent example built with nothing but Python, the OpenAI SDK and a while loop, written to accompany a blog article series that explains how agent frameworks work under the hood.

• Tutorials

autotune is a middleware layer that computes the exact KV cache a local LLM request needs, pins the system prompt in memory and manages context windows automatically for Ollama, LM Studio and Apple Silicon MLX, without any code or workflow changes.

• Inference

Invarail is a local, self-hosted authority layer for AI agents that separates what an agent is allowed to do from what it can learn to do, sitting in front of interchangeable workers for coding, repeatable procedures and open-ended tasks.

• Agent frameworks
• Security

Foreman keeps a project roadmap beside the code for Claude Code, Codex and Antigravity, and recommends the next task with its reasoning checked against the current state of the files before you start it.

• Agent skills

FerryAI runs ONNX, GGUF and RubixML models directly inside a PHP 8.3+ process through FFI, giving PHP applications chat, streaming, embeddings, RAG and vector search without a Python sidecar, HTTP microservice or Docker container.

• Inference

Crow is a local AI agent rather than a chat box: it gives a model around thirty tools, MCP access, memory, skills, goals, subagents, vision and image generation and editing, running on one GPU through its own engine or llama.cpp, or against any OpenRouter model.

• Agent frameworks
• Inference

CodexClaw is a Telegram bot that gives remote access to OpenAI Codex through a Node.js runtime, routing coding tasks, explicit tool calls and scheduled jobs to the right backend while keeping access restricted to a whitelist of users.

• Coding agents

ChipMATE is a multi-agent framework for generating Verilog RTL code in which a Verilog-writing agent and a Python reference-model agent cross-verify each other's outputs on random test inputs, needing no golden testbench.

• Coding agents
• Testing

Android Agent Harness is a provider-neutral Kotlin SDK for building bounded AI agents on Android and the JVM, with a governed run kernel, budgeted context, an approval protocol for risky actions and a reference sample app.

• Agent frameworks
• Mobile

This agentic CUDA kernel optimizer turns a plain-language workload description into a working GPU kernel by repeatedly generating code, checking correctness and benchmarking it, keeping the fastest validated version it finds.

• Coding agents

AgentClaw is a personal AI commander that understands intent, plans multi-step tasks and dispatches them to tools and skills, reachable through a web UI or through Telegram, WhatsApp, DingTalk, Feishu, QQ and WeCom, and doubling as a platform for hosting other independent agents.

• Agent frameworks

A knowledge base project documenting the internal structure of Windows Event Log resources, together with a Python module, winevtrc, for reusing that information in other tools.

• Libraries

An Android app that generates a real, installable APK on-device from a plain-language description, or from a website URL, injecting generated HTML/JS into a prebuilt WebView shell and giving it access to more than 30 native device bridges.

• Mobile

A Python-based simulation and control-development environment for PMSM motor "Fachschale" projects, supporting pure-Python and FMU/Modelica motor models with Differential Flatness Control, plus a C implementation for real-time execution on Infineon AURIX/TriCore hardware.

• Libraries

An agent-based graphic design workbench that turns chat instructions into editable design drafts using HTML, CSS and SVG as the underlying medium, with vector-quality export, multi-layer PSD output and lossless text rendering.

• Design tools

zerikai_memory is a standalone, local-only Python MCP server that gives any IDE persistent, workspace-isolated memory of a codebase's entities, built with deterministic tree-sitter parsing rather than an LLM-driven index.

• MCP servers
• Agent memory

SpecDD is a spec-driven development framework that keeps small, human-readable specification files beside the code they describe, giving both developers and AI coding agents one shared source of intent, boundaries and completion criteria.

• Agent skills

This is an end-to-end retrieval-augmented generation system for Chinese recipe question answering, covering data cleaning, hybrid retrieval, multi-turn conversation state and structured answer generation, verified with real end-to-end tests against a live model rather than mocks.

• RAG

PromptChain is a pip-installable library and MCP server for explicitly loading, unloading, pinning and swapping local language models across LM Studio and Ollama, plus a small Streamlit app that chains a drafting model into a coding model with a human review step in between.

• MCP servers
• Inference

NanoTeams is a free, open-source macOS app that runs an AI coding agent and coordinated multi-agent teams entirely on-device through Ollama or LM Studio, with an autonomous supervisor that can plan, run and review its own tasks.

• Coding agents

Meowary is a plain-Markdown work-journal template for software developers, maintained together with an AI coding agent so that architecture decisions, trade-offs and team context are captured once and recalled automatically before later work.

• Agent memory

MELLM routes a query to a small, domain-specific expert model instead of a single large general model, keeping only one specialist loaded in VRAM at a time so consumer GPUs can get expert-level answers.

• Inference
• LLM gateways