Alternatives
Products that do what Agenthatch – Compile any skill into a standalone Python agent does
- 1
- 2
- 3
- 4
- 5AP
I'm Guy, the founder behind Snyk — now building Tessl, a package manager for agent skills. We’ve recently witnessed that most teams still treat skills as static artifacts: markdown files, created or copied from repo to repo. This approach offers a strong initial boost, but quickly creates debt: - Skills are duplicated, and updates never roll out. - Poor quality skills go unseen, misguiding agents instead of helping. - Skill knowledge grows stale, and don’t keep up with the systems and practices they describe. Without a way to evaluate skills, teams have no clear way to understand how good a…
Feb 2026 · tessl.io
- 6
- 7RA
Hi HN! Sean from MindStudio here. I wanted to share something we've been working on that I think introduces some new ideas into the "AI coding agent" space. Remy is an AI agent that builds full-stack TypeScript apps from a spec written in a new flavor of annotated markdown. The spec has two layers: prose describing what the app does, and annotations that carry the technical precision (data types, edge cases, validation rules, code snippets). The agent then "compiles" this into code: backend methods, typed schemas, frontends, test scenarios, and everything else are derived artifacts of the…
Apr 2026 · remy.msagent.ai
- 8DA
Hey HN! Built a template for distributing AI agent skills via npm. Problem: AI coding tools (Claude Code, Cursor, Windsurf) support custom "skills" but distribution is manual - copy files to ~/.tool/skills/, repeat for updates, no versioning. Solution: Standard npm packages with lifecycle hooks: npm install -g @org/my-skill npm update -g @org/my-skill Benefits: - Semantic versioning (^1.2.0 for auto-updates) - Private registries for enterprise - Standard CI/CD integration - Discoverable on npmjs.com It's a GitHub template - fork, customize SKILL.md, publish.…
Jan 2026 · github.com
- 9AM
I have built many AI agents, and all frameworks felt so bloated, slow, and unpredictable. Therefore, I hacked together a minimal library that works with JSON/dict/kwargs definitions for each step, allowing you a simpler way to define reproducible agents. It supports concurrency for up to 1000 calls/min, giving you speed and predictability in your workflows. Install pip install flashlearn Input is a list of dictionaries Simply take user inputs, API responses, and calculations from other tools and feed them to FlashLearn. user_inputs = [{"query": "When was python launched?"}]…
2025 · github.com
- 10RT
Mar 2026 · github.com
- 11OS
May 2026 · 49agents.com
- 12
- 13UO
Hey HN, In the months since we initially released Burr (https://news.ycombinator.com/item?id=39917364), we have been hard at work. We wanted to share some of the most exciting changes we’ve made to build Burr out as a full-stack development framework for AI agents. In case you don’t recall, Burr is an open-source python library that makes it easier to build and debug GenAI applications & agents by representing them as graphs of simple python objects/functions. Burr only abstracts away system-level concerns (state persistence, debugging, observability), and does not…
2024 · burr.dagworks.io
- 14AR
Jul 2026 · github.com
- 15OS
I have been trying to create AI retool where tooling is done via AI, to create full stack apps like internal portals, ERP apps. Which led me to an architecture where we give ai pre build component, tools and let is just do the binding, content generation work to create full stack apps. With this approach in a single prompt AI is able to generate final config jsons using chained/looped agentic llm flow and we render a full stack app with the configs at the end. I have open sourced the whole project whole code, app builder, agentic architecture, backend for you to use. Github:…
2025 · oneshotcodegen.com
- 16SY
Mar 2026 · twill.ai
- 17ZG
Jun 2026 · zarldev.github.io
- 18TO
Jun 2026 · github.com
- 19AM
Jun 2026 · github.com
- 20
- 21AA
2025 · ashenfad.github.io
- 22LA
We combined Stanford's ACE (agents learning from execution feedback) with the Reflective Language Model pattern. Instead of reading traces in a single pass, an LLM writes and runs Python in a sandbox to programmatically explore them - finding cross-trace patterns that single-pass analysis misses. The framework achieved 2x consistency improvement on τ2-bench.
Mar 2026 · github.com
- 23JS
Oct 2025 · julius.ai
- 24
Run, review, and remember work across AI coding agents
10d ago · agentos.aiutil.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →