Pipevals
Evaluation pipelines for every LLM application
What it does
Evaluating LLM output by eyeballing it works... until it doesn’t. Pipevals is an open-source pipeline builder for AI evaluation. Trigger it with a single HTTP POST from your existing code, piping data through AI judges, scoring, and human review. Every run executes durably, with step-by-step results. Dashboards automatically track trends, distributions, and pass rates. Compare models, test prompts, and catch regressions. Self-hosted. MIT-licensed.
Does the same job
all alternatives →- PAPipevals – a visual pipeline builder for evaluation-driven AIMar 2026 · github.com · ▲6
Hey HN! Pipevals is early and rough (this is a learning project), but usable. It currently lets you: - build evaluation pipelines as graphs - run them against datasets - track how output quality changes over time
- PDPipelex – Declarative language for repeatable AI workflowsOct 2025 · github.com · ▲122
We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them. Why this instead of yet another workflow builder? - Declarative, not glue code: you state what to do; the runtime figures out how. - Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand. - Open…
- PLPipelines – Language for scripting parrallel pipelines with Python2019 · github.com · ▲69
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
