Hankweave: open-source framework for recursive self-optimization under $1000
hrishioa · x · 2026-10-14
The author details two years of work on open-source hankweave: one year to build, another to make it the most stable surface for long-horizon workflows. Core claim: post-Fable models with the right information and tooling can recursively self-optimize even in low-data, low-cost regimes (sub-1TB, under $1000). The key differentiator vs. loops-of-loops is knowledge ossified into expert instructions and tooling backed by a large library of learned patterns. On top of it you can integrate decision models into data-oriented tasks, build self-optimization loops, and pareto-surf to any point on the graph before deploying to the cloud.
More from coding & agent
- Scale CEO Ran an Agent Overnight to Direct and Edit a Full Video — alexandr_wang · 2026-10-14
- Connect Claude Code to NotebookLM via MCP to read full docs without burning tokens — Aiden_Tech_Ai · 2026-10-14
- SeedAudio 1.5 teased: AI-generated audio joins the video editing workflow in CapCut — FellMentKE · 2026-10-14
- How I built a 7-agent social media team for a legal consultant client — ifioknkem · 2026-10-14
- Pydantic's Samuel Colvin: Graph libraries are a mistake, your code IS the graph — samuelcolvin · 2026-10-14
- Sentience ships a web app built fully autonomously by agents while its human was on vacation — ditzikow · 2026-10-14