haft
Decision memory and governance layer for AI coding agents
Visit haft.tools ↗What is haft?
Haft is a governance substrate that gives AI coding agents durable project memory. It tracks what problems are being solved, which options were compared, what decisions were made, and what evidence supports them. The tool helps teams remember why they chose a particular approach and identifies when that reasoning has become stale due to changing conditions.
Built on the First Principles Framework by Anatoly Levenchuk, Haft integrates with Claude Code, Cursor, Gemini CLI, Codex, and other AI agents. It stores decision records as typed project graphs, keeping reversible reasoning in conversation while promoting critical decisions to durable records when handoff, replay, or verification requires them.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered haft automatically. Evidence: GitHub m0n0x41d/haft; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#2 this week
#7 this weekOpen-source design workspace that turns coding agents into a local design engine

Free, open-source video editor with auto-captions, effects, and 4K export

Manage teams of AI agents to run your business from one dashboard

Agent development environment for running multiple coding agents in parallel

AI converts documents into natively editable PowerPoint presentations

Open-source video production system directed by AI agents

Open-source AI job search agent that runs locally in your CLI