Pawl is a registry-as-ground-truth verification and autonomous research framework that ensures agent-driven development only advances on verified progress, recording both successes and honest negatives in a machine-readable CSV ledger.
92
No data
0
0
No data
2026-07-13
It directly addresses the critical flaw in agent-based coding—session amnesia—by providing a durable, queryable memory with frozen acceptance gates, dependency-linked registry, and first-class honest negatives, proven in a large-scale 590-claim case study with zero corruption.
Pawl
Registry-as-ground-truth verification & autonomous research framework for agent-driven development.
Coding agents don't remember. Every new session starts blind: what was already proven, what failed and why, which dead ends were closed for good — gone, buried in chat scrollback and stale plan documents. So agents re-try known failures, re-explore settled questions, and report "done" for work that no gate ever verified. Pawl fixes this by making progress itself a machine-readable artifact: every meaningful change is a claim with acceptance gates frozen before implementation, a CSV registry — not plans, not dashboards, not memory of a conversation — records what is actually implemented, and failures are written down as honest negatives that name the missing capability and permanently block the dead end. Like the mechanism it is named after — the small catch that lets a ratchet wheel turn forward but never slip back — Pawl makes verified progress the only direction the record can move. The origin project ran 590 claims through it in 18 days with 4–5 parallel agent sessions: 404 verified, 167 honest negatives, zero corrupted records (see the case study).
Works for any kind of software project — web app, library, ML project, CLI tool. Pure Python standard library, zero dependencies: adopt it by copying one folder and writing one small config file.
A pawl is the small catch in a ratchet mechanism — the part that engages the teeth of a ratchet wheel and lets it turn forward one click at a time, but blocks any backward slip. That is the whole metaphor: agent sessions should advance only on verified progress, and known dead ends should stay closed instead of being re-explored every time someone opens a fresh chat.
The name is also a nod to karpathy/autoresearch (March 2026), which uses the same ratchet idea for a single training file: keep improvements, discard regressions, one scalar, one budget. Pawl generalizes that loop to a whole repository — many concurrent claims, per-claim edit scopes, a persistent dependency-linked registry, and honest negatives promoted into the record instead of silently reset away.
Pawl is maintained and open-sourced by [Agentic Commerce Lab](https://github.com/agentic-c
Registry-as-ground-truth verification & autonomous research framework for agent-driven development.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.
