paper-instruments/feather-train
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A Python agent harness for knowledge work, with file and shell tools and skills for documents, spreadsheets, presentations, and PDFs. It runs locally against an OpenAI-compatible model, evaluates on Harbor tasks, and exports rollouts for model training.
Who it's for
Python developers building document-processing agents or evaluating and training LLM agents on office-style tasks
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up paper-instruments/feather-train in my project. Follow its README: https://github.com/paper-instruments/feather-train. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
18,265 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/paper-instruments/feather-train?ref=badge)Similar repos
- IsuruMaduranga/harness-engineering-101
A book-length series in Markdown that explains how AI agents work by building a roughly 300-line toy agent harness in plain Python. It covers the LLM message array, tool calls, the agent loop, context
- google-research/harness2
A Python framework for recursive harnessing of AI agents, which optimizes the prompts, tools, memory, skills and orchestration around a fixed model. It refines the harness per task through propose, pr
- N-tongxue/norman-skill
A collection of Python-based Skills for AI coding assistants supporting research workflows: converting paper figures into editable PowerPoint shapes, critical paper reading and research planning, and
- AntoGA/agents-contract
A template AGENTS.md contract for AI coding agents, a zero-dependency Python linter that checks it for required sections, placeholders, secrets and size, and a SessionStart hook that runs the linter a
- 15838328874/pi
A self-hostable, multi-tenant AI agent platform in Python, reimplementing the pi coding agent harness as an HTTP service. Includes streaming LLM adapters, an asyncio agent loop, sandboxed tool executi
- Harvil1/codeAgent
A terminal coding assistant that takes natural-language instructions, reads the repository, edits files, runs commands and tests, and iterates on multi-step changes. It supports OpenAI-compatible and