Alternatives

Products that do what Mini-swe-agent achieves 65% on SWE-bench in 100 lines of python does

1SS
Simple SWE agent in 72 lines of code (using Dagger)▲6
2025 · github.com
2PT
Pythonpy – the swiss army knife of the command line▲220
2014 · github.com
3AA
Algojammer – an experimental Python code editor inspired by Bret Victor▲309
2018 · github.com
4AP
A Python Spider System with Web UI▲159
2014 · github.com
5JA
Jarvis, a Light Table like companion for Python▲164
2012 · madlag.github.com
6FB
FastAPI: build Python APIs with Go-like speed and automatic UI docs▲88
2019 · fastapi.tiangolo.com
7SA
Sukhoi – A flexible and extensible Webcrawler in Python▲131
2017 · github.com
8IW
Ice – WSGI microframework to develop small web applications in Python▲53
2017 · icepy.readthedocs.io
9AA
Agex – An agent framework that lives in your Python runtime▲5
2025 · ashenfad.github.io
10MP
Minibatch – Python stream processing▲50
2020 · github.com
11IC
I created a Python framework for fast Slack bot development▲18
2015 · github.com
12AM
A multi-markup reader in less than 100 lines of Python code▲30
2020 · gist.github.com
13AR
A registry of agent benchmarks (including many OSS agent trajectories)▲6
If you're interested in exploring what LLM-based agent systems these days actually do to solve certain benchmarks such as SWEBench or WebArena, we created a small leaderboard with our team, that allows to view a lot of public and OSS agent results including all the runtime traces (the step-by-step reasoning behind the scenes). Looking at traces is actually quite interesting, as they reveal a lot about the inner working and shortcomings of current agent system, e.g. see https://explorer.invariantlabs.ai/u/invariant/webarena--SteP... for an example trace.
2024 · explorer.invariantlabs.ai
14LA
LanderDB – A Mini Flat File Database Engine for Python▲27
2015 · github.com
15AA
Axe – A CLI for running single-purpose LLM agents▲6
Mar 2026 · github.com
16RS
Randomly switching between LMs at every step boosts SWE-bench score▲5
What if your agent uses a different LM at every turn? We let mini-SWE-agent randomly switch between GPT-5 and Sonnet 4 and it scored higher on SWE-bench than with either model separately. GPT-5 by itself gets 65.0%, Sonnet 4 64.8%, but randomly switching at every step gets us 67.2% This result came pretty surprising to us. There's a few more experiments in the blog post.
2025 · swebench.com
17OS
Open-source 2D IDE for managing agent CLIs▲9
May 2026 · 49agents.com
18MD
ML-Dev-Bench – Benchmarking AI Agents on Real-World AI Workflows▲6
We’re excited to share ML-Dev-Bench, a new open-source benchmark that tests AI agents on real-world ML development tasks. Unlike typical coding challenges or Kaggle-style competitions, our benchmark simulates end-to-end ML workflows including: - Dataset handling and preprocessing - Debugging model and code failures - Implementing new model architectures - Fine-tuning and improving existing models With 30 diverse tasks, ML-Dev-Bench evaluates agents across critical stages of ML development. To complement this, we built Calipers, a framework that provides systematic performance evaluation and…
2025 · github.com
19FM
Faster ML Prototyping▲7
2020 · github.com
20MA
minigrad – a minimal, educational autograd library (~100 loc in Python)▲5
2020 · github.com
21OA
Onlymaps, a Python Micro-ORM▲5
Nov 2025 · github.com
22ST
Slacky, the first open-source Slack selfbot in Python▲10
2020 · github.com
23MR
Minima-RAG On-Premises Python Framework▲5
2024 · github.com
24LA
LLM agents that write Python to analyze execution traces at scale▲5
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

Ranked by how close each launch is in meaning, then by votes. Refine with a description →