Moatless Tools

Hobby project for LLM code editing in large codebases, run via Docker with a web UI and a SWE-bench harness.

Agent by Albert Örwall

IndexedMIT★ 642

Write a review

Get started

Setup steps are in the repository. Repository

About

Moatless Tools is a hobby project by its author that tests the idea that good tools for inserting context and handling responses matter more than having an agent reason its way to a solution. It runs in Docker with a UI at localhost, can be installed from PyPI as the moatless package, and includes a Python agent API and SWE-bench evaluation scripts. The README reports a 70.8% solve rate at $0.63 per instance for Claude 4 Sonnet on SWE-bench. Evaluations need at least one LLM provider key and a Voyage AI key for pre-embedded vector stores.

Use cases: coding, code-generation, llm-evaluation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: codingREADME
Where you use it: WebREADME
Hosting: You run itREADME
Models: openai, anthropic, openrouterREADME
Open source: Yes

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Built on

Frameworks named in its dependency files.

0.853score
LlamaIndex
LlamaIndex
Open-source Python toolkit for RAG and agents over your own data, with event-driven workflows and 300+ integration packages.
HarnessAFreshness: A★ 52.6K↓ 1.4M/wk

Signals

Stars: 642
Forks: 61
Open issues: 18
Last commit: Sep 1, 2025 (1 year ago)
Last release: Jun 7, 2025 (1 year ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/aorwall/moatless-tools
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Cite this page

Moatless Tools. Agent Mart. https://agentmart.dev/agents/moatless-tools (last updated 2026-10-24)