MCP servers and skills: search, filter by where they run, and compare.
Irish rent, rent limits, house price comps (IE, NL, EU), housing report. x402/MPP paid.
Hosted by authorNo licenseFew starsNo key
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scena
OfficialPythonApache-2.0★ 2.4kNo key
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w
PythonMIT★ 32kNo key
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
SkillGPL-3.0★ 42kNo key
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section.
PythonMIT★ 1.2kNo key
AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative wi
DockerMIT★ 1.2kNo key
Open-source desktop coding agent that matches Codex on Terminal-Bench 2.1 with 63% fewer tokens.
Node.jsApache-2.0★ 143No key
Deterministic context compressor for MCP agents. Slots in front of prompt caching, mem0, Letta, or Claude Code. Single Rust binary, zero ML at query time.
Node.jsMIT★ 9No key
Open-source robotics simulator for coding agents: HTTP/JSON + MCP control, Newton physics, wgpu rendering, ROS 2, and reproducible benchmarks.
SkillApache-2.0★ 188No key
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
SkillApache-2.0★ 102No key
Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.
PythonMIT★ 32No key
Benchmark local LLM inference engines (llama.cpp, omlx) on your own hardware with real tokens/sec, not borrowed numbers
PythonApache-2.0Few starsNo key
Local-first memory for AI coding assistants. Verbatim, on your PC — 88.8% on LongMemEval with zero model calls at write time.
PythonAGPL-3.0★ 2Few starsNo key
Create Word, Excel, and PowerPoint files (.docx, .xlsx, .pptx) from plain JSON or fully typed APIs — generate, parse, and patch. Built for AI agents, LLM tool-calling, and hand-written code alike; no
SkillMIT★ 38No key
Auditable code intelligence for AI agents - map dependencies, predict change impact, select the right tests, and verify refactors before they ship.
Hosted by authorAGPL-3.0★ 31No key
A CLI tool that outputs XML/JSON, built for AI agents to consume directly.
GoMIT★ 17No key
Smart JSON-to-TOON conversion with pragmatic auto-gating for LLM prompts
PythonMIT★ 2Few starsNo key
Handle-ifying MCP proxy: slash token bills on chatty MCP servers via content-aware backends and local munch verbs
PythonMIT★ 33No key
Node.jsMITFew starsNo key
Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.
PythonApache-2.0★ 9No key
Node.jsMIT★ 4Few starsNo key
Near-lock-free structured logging for Rust: a 65,536-slot ring buffer, formatting deferred to a background thread, 14 output formats (JSON, ECS, GELF, OTLP, logfmt…) and native os_log/journald sinks.
DockerApache-2.0★ 6No key
Who stands behind it
