mini-swe-agent
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores 68% on SWE-bench verified!
Stars: 1593
The mini-swe-agent is a lightweight AI agent designed to solve GitHub issues and more. It is a minimal tool with just 100 lines of Python code, suitable for researchers, developers, and engineers looking for a simple, powerful, and deployable solution. The agent is built to be convenient, deployable in various environments, and tested for performance. It focuses on providing a hackable tool that is simple, convenient, and flexible, without unnecessary bloat or complexity. Users can run the agent with any model using bash, making it ideal for benchmarking, fine-tuning, and reinforcement learning tasks.
README:
📣 New blogpost: Randomly switching between GPT-5 and Sonnet 4 boosts performance
In 2024, SWE-bench & SWE-agent helped kickstart the coding agent revolution.
We now ask: What if SWE-agent was 100x smaller, and still worked nearly as well?
mini is for
- Researchers who want to benchmark, fine-tune or RL without assumptions, bloat, or surprises
- Developers who like their tools like their scripts: short, sharp, and readable
- Engineers who want something trivial to sandbox & to deploy anywhere
Here's some details:
- Minimal: Just 100 lines of python (+100 total for env, model, script) — no fancy dependencies!
- Powerful: Resolves 68% of GitHub issues in the SWE-bench verified benchmark (leaderboard).
- Convenient: Comes with UIs that turn this into your daily dev swiss army knife!
- Deployable: In addition to local envs, you can use docker, podman, singularity, apptainer, and more
-
Tested:
- Cutting edge: Built by the Princeton & Stanford team behind SWE-bench and SWE-agent.
More motivation (for research)
SWE-agent jump-started the development of AI agents in 2024. Back then, we placed a lot of emphasis on tools and special interfaces for the agent. However, one year later, as LMs have become more capable, a lot of this is not needed at all to build a useful agent! In fact, mini-SWE-agent
- Does not have any tools other than bash — it doesn't even use the tool-calling interface of the LMs. This means that you can run it with literally any model. When running in sandboxed environments you also don't need to take care of installing a single package — all it needs is bash.
- Has a completely linear history — every step of the agent just appends to the messages and that's it. So there's no difference between the trajectory and the messages that you pass on to the LM. Great for debugging & fine-tuning.
-
Executes actions with
subprocess.run— every action is completely independent (as opposed to keeping a stateful shell session running). This makes it trivial to execute the actions in sandboxes (literally just switch outsubprocess.runwithdocker exec) and to scale up effortlessly. Seriously, this is a big deal, trust me.
This makes it perfect as a baseline system and for a system that puts the language model (rather than
the agent scaffold) in the middle of our attention.
You can see the result on the SWE-bench (bash only) leaderboard, that evaluates the performance of different LMs with mini.
More motivation (as a tool)
Some agents are overfitted research artifacts. Others are UI-heavy frontend monsters.
mini wants to be a hackable tool, not a black box.
- Simple enough to understand at a glance
- Convenient enough to use in daily workflows
- Flexible to extend
Unlike other agents (including our own swe-agent), it is radically simpler, because it:
- Does not have any tools other than bash — it doesn't even use the tool-calling interface of the LMs. Instead of implementing custom tools for every specific thing the agent might want to do, the focus is fully on the LM utilizing the shell to its full potential. Want it to do something specific like opening a PR? Just tell the LM to figure it out rather than spending time to implement it in the agent.
-
Executes actions with
subprocess.run— every action is completely independent (as opposed to keeping a stateful shell session running). This is a big deal for the stability of the agent, trust me. - Has a completely linear history — every step of the agent just appends to the messages that are passed to the LM in the next step and that's it. This is great for debugging and understanding what the LM is prompted with.
Should I use SWE-agent or mini-SWE-agent?
You should use mini-swe-agent if
- You want a quick command line tool that works locally
- You want an agent with a very simple control flow
- You want even faster, simpler & more stable sandboxing & benchmark evaluations
- You are doing FT or RL and don't want to overfit to a specific agent scaffold
You should use swe-agent if
- You need specific tools or want to experiment with different tools
- You want to experiment with different history processors
- You want very powerful yaml configuration without touching code
What you get with both
- Excellent performance on SWE-Bench
- A trajectory browser
Simple UI (mini)
|
Visual UI (mini -v)
|
|
|
|
| Batch inference | Trajectory browser |
|
|
|
| Python bindings | More in the docs |
agent = DefaultAgent(
LitellmModel(model_name=...),
LocalEnvironment(),
)
agent.run("Write a sudoku game") |
Option 1: Install + run in virtual environment
pip install uv && uvx mini-swe-agent [-v]
# or
pip install pipx && pipx ensurepath && pipx run mini-swe-agent [-v]Option 2: Install in current environment
pip install mini-swe-agent && mini [-v]Option 3: Install from source
git clone https://github.com/SWE-agent/mini-swe-agent.git
cd mini-swe-agent
pip install -e .
mini [-v]Read more in our documentation:
If you found this work helpful, please consider citing the SWE-agent paper in your work:
@inproceedings{yang2024sweagent,
title={{SWE}-agent: Agent-Computer Interfaces Enable Automated Software Engineering},
author={John Yang and Carlos E Jimenez and Alexander Wettig and Kilian Lieret and Shunyu Yao and Karthik R Narasimhan and Ofir Press},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://arxiv.org/abs/2405.15793}
}Our other projects:
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for mini-swe-agent
Similar Open Source Tools
mini-swe-agent
The mini-swe-agent is a lightweight AI agent designed to solve GitHub issues and more. It is a minimal tool with just 100 lines of Python code, suitable for researchers, developers, and engineers looking for a simple, powerful, and deployable solution. The agent is built to be convenient, deployable in various environments, and tested for performance. It focuses on providing a hackable tool that is simple, convenient, and flexible, without unnecessary bloat or complexity. Users can run the agent with any model using bash, making it ideal for benchmarking, fine-tuning, and reinforcement learning tasks.
langflow
Langflow is an open-source Python-powered visual framework designed for building multi-agent and RAG applications. It is fully customizable, language model agnostic, and vector store agnostic. Users can easily create flows by dragging components onto the canvas, connect them, and export the flow as a JSON file. Langflow also provides a command-line interface (CLI) for easy management and configuration, allowing users to customize the behavior of Langflow for development or specialized deployment scenarios. The tool can be deployed on various platforms such as Google Cloud Platform, Railway, and Render. Contributors are welcome to enhance the project on GitHub by following the contributing guidelines.
lanarky
Lanarky is a Python web framework designed for building microservices using Large Language Models (LLMs). It is LLM-first, fast, modern, supports streaming over HTTP and WebSockets, and is open-source. The framework provides an abstraction layer for developers to easily create LLM microservices. Lanarky guarantees zero vendor lock-in and is free to use. It is built on top of FastAPI and offers features familiar to FastAPI users. The project is now in maintenance mode, with no active development planned, but community contributions are encouraged.
Open-LLM-VTuber
Open-LLM-VTuber is a voice-interactive AI companion supporting real-time voice conversations and featuring a Live2D avatar. It can run offline on Windows, macOS, and Linux, offering web and desktop client modes. Users can customize appearance and persona, with rich LLM inference, text-to-speech, and speech recognition support. The project is highly customizable, extensible, and actively developed with exciting features planned. It provides privacy with offline mode, persistent chat logs, and various interaction features like voice interruption, touch feedback, Live2D expressions, pet mode, and more.
moai
moai is a PyTorch-based AI Model Development Kit (MDK) designed to improve data-driven model workflows, design, and understanding. It offers modularity via monads for model building blocks, reproducibility via configuration-based design, productivity via a data-driven domain modelling language (DML), extensibility via plugins, and understanding via inter-model performance and design aggregation. The tool provides specific integrated actions like play, train, evaluate, plot, diff, and reprod to support heavy data-driven workflows with analytics, knowledge extraction, and reproduction. moai relies on PyTorch, Lightning, Hydra, TorchServe, ONNX, Visdom, HiPlot, Kornia, Albumentations, and the wider open-source community for its functionalities.
colors_ai
Colors AI is a cross-platform color scheme generator that uses deep learning from public API providers. It is available for all mainstream operating systems, including mobile. Features: - Choose from open APIs, with the ability to set up custom settings - Export section with many export formats to save or clipboard copy - URL providers to other static color generators - Localized to several languages - Dark and light theme - Material Design 3 - Data encryption - Accessibility - And much more
kalavai-client
Kalavai is an open-source platform that transforms everyday devices into an AI supercomputer by aggregating resources from multiple machines. It facilitates matchmaking of resources for large AI projects, making AI hardware accessible and affordable. Users can create local and public pools, connect with the community's resources, and share computing power. The platform aims to be a management layer for research groups and organizations, enabling users to unlock the power of existing hardware without needing a devops team. Kalavai CLI tool helps manage both versions of the platform.
mlflow
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are:
* `MLflow Tracking
neuro-san-studio
Neuro SAN Studio is an open-source library for building agent networks across various industries. It simplifies the development of collaborative AI systems by enabling users to create sophisticated multi-agent applications using declarative configuration files. The tool offers features like data-driven configuration, adaptive communication protocols, safe data handling, dynamic agent network designer, flexible tool integration, robust traceability, and cloud-agnostic deployment. It has been used in various use-cases such as automated generation of multi-agent configurations, airline policy assistance, banking operations, market analysis in consumer packaged goods, insurance claims processing, intranet knowledge management, retail operations, telco network support, therapy vignette supervision, and more.
LLM-Zero-to-Hundred
LLM-Zero-to-Hundred is a repository showcasing various applications of LLM chatbots and providing insights into training and fine-tuning Language Models. It includes projects like WebGPT, RAG-GPT, WebRAGQuery, LLM Full Finetuning, RAG-Master LLamaindex vs Langchain, open-source-RAG-GEMMA, and HUMAIN: Advanced Multimodal, Multitask Chatbot. The projects cover features like ChatGPT-like interaction, RAG capabilities, image generation and understanding, DuckDuckGo integration, summarization, text and voice interaction, and memory access. Tutorials include LLM Function Calling and Visualizing Text Vectorization. The projects have a general structure with folders for README, HELPER, .env, configs, data, src, images, and utils.
data-juicer
Data-Juicer is a one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs. It is a systematic & reusable library of 80+ core OPs, 20+ reusable config recipes, and 20+ feature-rich dedicated toolkits, designed to function independently of specific LLM datasets and processing pipelines. Data-Juicer allows detailed data analyses with an automated report generation feature for a deeper understanding of your dataset. Coupled with multi-dimension automatic evaluation capabilities, it supports a timely feedback loop at multiple stages in the LLM development process. Data-Juicer offers tens of pre-built data processing recipes for pre-training, fine-tuning, en, zh, and more scenarios. It provides a speedy data processing pipeline requiring less memory and CPU usage, optimized for maximum productivity. Data-Juicer is flexible & extensible, accommodating most types of data formats and allowing flexible combinations of OPs. It is designed for simplicity, with comprehensive documentation, easy start guides and demo configs, and intuitive configuration with simple adding/removing OPs from existing configs.
agentkit
AgentKit is a framework developed by Coinbase Developer Platform for enabling AI agents to take actions onchain. It is designed to be framework-agnostic and wallet-agnostic, allowing users to integrate it with any AI framework and any wallet. The tool is actively being developed and encourages community contributions. AgentKit provides support for various protocols, frameworks, wallets, and networks, making it versatile for blockchain transactions and API integrations using natural language inputs.
lingoose
LinGoose is a modular Go framework designed for building AI/LLM applications. It offers the flexibility to import only the necessary modules, abstracts features for customization, and provides a comprehensive solution for developing AI/LLM applications from scratch. The framework simplifies the process of creating intelligent applications by allowing users to choose preferred implementations or create their own. LinGoose empowers developers to leverage its capabilities to streamline the development of cutting-edge AI and LLM projects.
toolhive
ToolHive is a tool designed to simplify and secure Model Context Protocol (MCP) servers. It allows users to easily discover, deploy, and manage MCP servers by launching them in isolated containers with minimal setup and security concerns. The tool offers instant deployment, secure default settings, compatibility with Docker and Kubernetes, seamless integration with popular clients, and availability as a GUI desktop app, CLI, and Kubernetes Operator.
ComfyUI-HunyuanVideo-Nyan
ComfyUI-HunyuanVideo-Nyan is a repository that provides tools for manipulating the attention of LLM models, allowing users to shuffle the AI's attention and cause confusion. The repository includes a Nerdy Transformer Shuffle node that enables users to mess with the LLM's attention layers, providing a workflow for installation and usage. It also offers a new SAE-informed Long-CLIP model with high accuracy, along with recommendations for CLIP models. Users can find detailed instructions on how to use the provided nodes to scale CLIP & LLM factors and create high-quality nature videos. The repository emphasizes compatibility with other related tools and provides insights into the functionality of the included nodes.
langgraph-mcp-agents
LangGraph Agent with MCP is a toolkit provided by LangChain AI that enables AI agents to interact with external tools and data sources through the Model Context Protocol (MCP). It offers a user-friendly interface for deploying ReAct agents to access various data sources and APIs through MCP tools. The toolkit includes features such as a Streamlit Interface for interaction, Tool Management for adding and configuring MCP tools dynamically, Streaming Responses in real-time, and Conversation History tracking.
For similar tasks
arena-hard-auto
Arena-Hard-Auto-v0.1 is an automatic evaluation tool for instruction-tuned LLMs. It contains 500 challenging user queries. The tool prompts GPT-4-Turbo as a judge to compare models' responses against a baseline model (default: GPT-4-0314). Arena-Hard-Auto employs an automatic judge as a cheaper and faster approximator to human preference. It has the highest correlation and separability to Chatbot Arena among popular open-ended LLM benchmarks. Users can evaluate their models' performance on Chatbot Arena by using Arena-Hard-Auto.
max
The Modular Accelerated Xecution (MAX) platform is an integrated suite of AI libraries, tools, and technologies that unifies commonly fragmented AI deployment workflows. MAX accelerates time to market for the latest innovations by giving AI developers a single toolchain that unlocks full programmability, unparalleled performance, and seamless hardware portability.
ai-hub
AI Hub Project aims to continuously test and evaluate mainstream large language models, while accumulating and managing various effective model invocation prompts. It has integrated all mainstream large language models in China, including OpenAI GPT-4 Turbo, Baidu ERNIE-Bot-4, Tencent ChatPro, MiniMax abab5.5-chat, and more. The project plans to continuously track, integrate, and evaluate new models. Users can access the models through REST services or Java code integration. The project also provides a testing suite for translation, coding, and benchmark testing.
long-context-attention
Long-Context-Attention (YunChang) is a unified sequence parallel approach that combines the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention to provide a versatile and high-performance solution for long context LLM model training and inference. It addresses the limitations of both methods by offering no limitation on the number of heads, compatibility with advanced parallel strategies, and enhanced performance benchmarks. The tool is verified in Megatron-LM and offers best practices for 4D parallelism, making it suitable for various attention mechanisms and parallel computing advancements.
marlin
Marlin is a highly optimized FP16xINT4 matmul kernel designed for large language model (LLM) inference, offering close to ideal speedups up to batchsizes of 16-32 tokens. It is suitable for larger-scale serving, speculative decoding, and advanced multi-inference schemes like CoT-Majority. Marlin achieves optimal performance by utilizing various techniques and optimizations to fully leverage GPU resources, ensuring efficient computation and memory management.
MMC
This repository, MMC, focuses on advancing multimodal chart understanding through large-scale instruction tuning. It introduces a dataset supporting various tasks and chart types, a benchmark for evaluating reasoning capabilities over charts, and an assistant achieving state-of-the-art performance on chart QA benchmarks. The repository provides data for chart-text alignment, benchmarking, and instruction tuning, along with existing datasets used in experiments. Additionally, it offers a Gradio demo for the MMCA model.
Tiktoken
Tiktoken is a high-performance implementation focused on token count operations. It provides various encodings like o200k_base, cl100k_base, r50k_base, p50k_base, and p50k_edit. Users can easily encode and decode text using the provided API. The repository also includes a benchmark console app for performance tracking. Contributions in the form of PRs are welcome.
ppl.llm.serving
ppl.llm.serving is a serving component for Large Language Models (LLMs) within the PPL.LLM system. It provides a server based on gRPC and supports inference for LLaMA. The repository includes instructions for prerequisites, quick start guide, model exporting, server setup, client usage, benchmarking, and offline inference. Users can refer to the LLaMA Guide for more details on using this serving component.
For similar jobs
Pichome
PicHome is a powerful open-source cloud storage program that efficiently manages various types of files and excels in image and media file management. Its highlights include robust file sharing features and advanced AI-assisted management tools, providing users with a convenient and intelligent file management experience. The program offers diverse list modes, customizable file information display, enhanced quick file preview, advanced tagging, custom cover and preview images, multiple preview images, and multi-library management. Additionally, PicHome features strong file sharing capabilities, allowing users to share entire libraries, create personalized showcase web pages, and build complete data sharing websites. The AI-assisted management aspect includes AI file renaming, tagging, description writing, batch annotation, and file Q&A services, all aimed at improving file management efficiency. PicHome supports a wide range of file formats and can be applied in various scenarios such as e-commerce, gaming, design, development, enterprises, schools, labs, media, and entertainment institutions.
machine-learning-research
The 'machine-learning-research' repository is a comprehensive collection of resources related to mathematics, machine learning, deep learning, artificial intelligence, data science, and various scientific fields. It includes materials such as courses, tutorials, books, podcasts, communities, online courses, papers, and dissertations. The repository covers topics ranging from fundamental math skills to advanced machine learning concepts, with a focus on applications in healthcare, genetics, computational biology, precision health, and AI in science. It serves as a valuable resource for individuals interested in learning and researching in the fields of machine learning and related disciplines.
Awesome-TimeSeries-SpatioTemporal-LM-LLM
Awesome-TimeSeries-SpatioTemporal-LM-LLM is a curated list of Large (Language) Models and Foundation Models for Temporal Data, including Time Series, Spatio-temporal, and Event Data. The repository aims to summarize recent advances in Large Models and Foundation Models for Time Series and Spatio-Temporal Data with resources such as papers, code, and data. It covers various applications like General Time Series Analysis, Transportation, Finance, Healthcare, Event Analysis, Climate, Video Data, and more. The repository also includes related resources, surveys, and papers on Large Language Models, Foundation Models, and their applications in AIOps.
moon
Moon is a monitoring and alerting platform suitable for multiple domains, supporting various application scenarios such as cloud-native, Internet of Things (IoT), and Artificial Intelligence (AI). It simplifies operational work of cloud-native monitoring, boasts strong IoT and AI support capabilities, and meets diverse monitoring needs across industries. Capable of real-time data monitoring, intelligent alerts, and fault response for various fields.
DownEdit
DownEdit is a fast and powerful program for downloading and editing videos from platforms like TikTok, Douyin, and Kuaishou. It allows users to effortlessly grab videos, make bulk edits, and utilize advanced AI features for generating videos, images, and sounds in bulk. The tool offers features like video, photo, and sound editing, downloading videos without watermarks, bulk AI generation, and AI editing for content enhancement.
ai-trend-publish
AI TrendPublish is an AI-based trend discovery and content publishing system that supports multi-source data collection, intelligent summarization, and automatic publishing to WeChat official accounts. It features data collection from various sources, AI-powered content processing using DeepseekAI Together, key information extraction, intelligent title generation, automatic article publishing to WeChat official accounts with custom templates and scheduled tasks, notification system integration with Bark for task status updates and error alerts. The tool offers multiple templates for content customization and is built using Node.js + TypeScript with AI services from DeepseekAI Together, data sources including Twitter/X API and FireCrawl, and uses node-cron for scheduling tasks and EJS as the template engine.
llm.hunyuan.T1
Hunyuan-T1 is a cutting-edge large-scale hybrid Mamba reasoning model driven by reinforcement learning. It has been officially released as an upgrade to the Hunyuan Thinker-1-Preview model. The model showcases exceptional performance in deep reasoning tasks, leveraging the TurboS base and Mamba architecture to enhance inference capabilities and align with human preferences. With a focus on reinforcement learning training, the model excels in various reasoning tasks across different domains, showcasing superior abilities in mathematical, logical, scientific, and coding reasoning. Through innovative training strategies and alignment with human preferences, Hunyuan-T1 demonstrates remarkable performance in public benchmarks and internal evaluations, positioning itself as a leading model in the field of reasoning.
DownEdit
DownEdit is a fast and powerful program for downloading and editing videos from top platforms like TikTok, Douyin, and Kuaishou. Effortlessly grab videos from user profiles, make bulk edits throughout the entire directory with just one click. Advanced Chat & AI features let you download, edit, and generate videos, images, and sounds in bulk. Exciting new features are coming soon—stay tuned!