Aqven — AI skill for Claude Code
Python framework + local Studio for reliable LLM workflows: typed files in your repo, pre-run checks, experiments and evals, MCP server for coding agents.
How to install Aqven
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lastonoga/AQVEN and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Aqven does
Python framework + local Studio for reliable LLM workflows: typed files in your repo, pre-run checks, experiments and evals, MCP server for coding agents.
Alternatives in AI
- Matlab MCP Server — Run MATLAB® using AI applications with the official MATLAB MCP Server from MathWorks® 1.4k ★
- TurboLLM — Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API 251 ★
- Dataverse Skills — Microsoft Dataverse skills for AI coding agents 209 ★
README
AQVEN
Discover what your AI workflow needs to work reliably.
AQVEN is a Python framework and a local Studio for building reliable LLM workflows: multi-step pipelines of models, tools and human review.
Your coding agent runs the experiments. You see the evidence and decide.
[](https://pypi.org/project/aqven/) [](https://pypi.org/project/aqven/) [](https://github.com/lastonoga/AQVEN/actions/workflows/ci.yml) [](LICENSE)
**[Documentation](https://aqvenstudio.com)** · **[Quickstart](https://aqvenstudio.com/start/quickstart/)** · **[Use cases](https://aqvenstudio.com/use-cases/)** · **[Studio](https://aqvenstudio.com/studio/)** · **[llms.txt](https://aqvenstudio.com/llms.txt)**
AQVEN keeps an AI workflow as typed files in your repository: a flow, one file per step, prompts in Markdown, and declared types, agents and tools. `aqven check` validates every connection and simulates every flow before you spend a token. Studio, a local browser app in the same install, shows each run step by step. Your coding agent (Claude Code, Codex or any MCP client) works on the same files through AQVEN's MCP server, and runs experiments whose verdicts AQVEN computes.
[!NOTE] AQVEN is in alpha: expect changes between releases. It is source-available, not open source. See [License](#license).
Contents
- What it's for
- Install
- Start with your coding agent
- Start by hand
- [Your agent does the work. You direct the investigation.](#your-agent-does-the-work-you-direct-the-in
Related Skills
Octoroute
Smart HTTP router for local LLMs (Ollama, LM Studio, llama.cpp). Rule-based + LLM-powered routing, health chec
CEGM
Live LLM-driven Cheat Engine layer with MCP HTTP and a local dashboard for single-player offline experiments
RAG Support Agent
Financial document AI: evidence-checked extraction (structured outputs), RAG Q&A with page citations, a tool-c
Afm Studio
Apple's on-device foundation model as a Mac app, a CLI, an MCP server for Claude, and a local OpenAI-compatibl
Folder Lock
Many AI agents, one repo, no conflicting saves - a Claude Code skill: one lock per workfolder, handoffs instea
Counterfactual Statistics
Statistics for counterfactual and paired-branch ML experiments - the independent unit, paired tests against a
Related Agents
AI Backend Engineer
AI Backend Engineer who builds scalable, reliable server-side systems powering AI applications — including API
Eval Schema
Eval arm schema (minimal + typed schemas, no prose). Answers one building-data question using ONLY the eval-sc
Local Worker
Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream. Use whe