# SWE-agent

> Source: https://agentsindex.ai/swe-agent

An LM-driven agent for repository-level coding tasks.

Starting price

Free

From [swe-agent.com](https://swe-agent.com/), checked 28 October 2026

- MCP server Not stated
- API Not stated
- Open source Yes Checked by us github.com/SWE-agent/SWE-agent/blob/main/LICENSE, 15 November 2026 [Checked by us](https://github.com/SWE-agent/SWE-agent/blob/main/LICENSE)
- Self-host Yes

- GitHub stars: 20.6k

[Docs](https://swe-agent.com/latest/) [GitHub](https://github.com/SWE-agent/SWE-agent)

What we checked

- Pages last read: 15 November 2026
- Facts checked: 1 fact · From 2 sources
- AI answers: Too few read · 58 buyer-question answers read, November 2026

[How we check](https://agentsindex.ai/methodology) [Editorial policy](https://agentsindex.ai/editorial-policy#not-for-sale)

[Visit SWE-agent](https://agentsindex.ai/go/swe-agent) [Compare](https://agentsindex.ai/compare?cat=coding-agents&products=swe-agent)

## At a glance

- Category: [Coding agents](https://agentsindex.ai/categories/coding-agents)
- Tags: Free, Open source, Self-hosted

### Code

- Last push: 12 October 2026

### For developers

- Runs: Self-hosted
- Works with: GitHub, Slack

## SWE-agent in our research

[All research](https://agentsindex.ai/blog)

Study 19 October 2026 – 16 November 2026

### [AI Tool Pricing Index, November 2026](https://agentsindex.ai/data/ai-tool-pricing-index)

Pricing

Free only

29 of the 361 tools we checked are free with no paid plan.

Edition price, checked 28 October 2026.

Pricing pages of the AI tools, November 2026 edition as of 16 November 2026 n = 361 tools checked

## What it actually is

SWE-agent (Princeton NLP, first released April 2024, presented at NeurIPS 2024) takes a GitHub issue and an LLM of your choice, and lets the model browse, edit, and execute code inside a sandboxed Docker container through a purpose-built command set the authors call an Agent-Computer Interface (ACI) — structured file-viewing, editing, and search commands designed to be easier for an LLM to use reliably than a raw shell. That ACI framing was the project's genuine research contribution and is documented in the NeurIPS paper. ([github.com/SWE-agent/SWE-agent](https://github.com/SWE-agent/SWE-agent), [collaborate.princeton.edu/en/publications/swe-agent-agent-computer-interfaces-enable-automated-software-eng](https://collaborate.princeton.edu/en/publications/swe-agent-agent-computer-interfaces-enable-automated-software-eng/))

## The project told us not to use it

The docs site (swe-agent.com) currently shows a banner reading "SWE-agent is now in maintenance-only mode" and a popup recommending mini-swe-agent instead, with the stated reason "Same performance, much more simple." This isn't a rumor or a stale note — it's the live, vendor-authored front page of the docs as of today. GitHub activity backs up the "maintenance" label: SWE-agent/SWE-agent still received bug-fix and doc-correction commits through July 2026 (most recently merged 16 July 2026), and the repo was pushed to as recently as 17 August 2026, but the last tagged release is v1.1.0 from May 2025 — over a year with no new version, while commits keep landing on main. Read that as: bugs get fixed, nothing new ships. mini-swe-agent, from the same GitHub org, is under active version releases (v2.0.0 as of this year) and is what the team is putting effort into now. ([swe-agent.com/latest](https://swe-agent.com/latest/), [github.com/SWE-agent/SWE-agent/commits/main](https://github.com/SWE-agent/SWE-agent/commits/main), [github.com/SWE-agent/SWE-agent/releases](https://github.com/SWE-agent/SWE-agent/releases))

## Benchmark standing: real, but it's mini-swe-agent's now

On the official SWE-bench leaderboard (swebench.com), the harness labeled "mini-SWE-agent" appears in 107 separate result rows — used by Anthropic, OpenAI, Google DeepMind, Moonshot, Z-AI and others to report official SWE-bench Verified scores for their models — with resolve rates up to 76.8% for the strongest model/harness pairing found today. The original "SWE-agent" harness has 20 rows on the same leaderboard, reflecting its earlier, lower-ceiling era (the 2024 launch figure widely cited was 12.29% resolved with GPT-4). In short: the ACI concept SWE-agent introduced won, but the numbers you'd want to quote today belong to the successor project, not this one. ([swebench.com](https://www.swebench.com/))

## Cost and licensing

Free and MIT-licensed (confirmed via the GitHub API license field), runs entirely on infrastructure you control, and has no vendor pricing page because there's no vendor — you pay only for the LLM API calls it makes on your behalf and, if you use the default setup, for Docker container time. There is no hosted or managed offering; this is a self-run CLI/library. ([api.github.com/repos/SWE-agent/SWE-agent](https://api.github.com/repos/SWE-agent/SWE-agent))

## A packaging trap: don't use the PyPI package

The `sweagent` package on PyPI is real (published by the actual author, John Yang) but stuck at version 0.0.1, uploaded 2 April 2024 and never updated since — while the GitHub project has moved through v1.1.0 and well beyond in active commits. `pip install sweagent` will not get you a working, current copy of the tool; the project's own install docs point to cloning the repo and running `pip install --editable.` from source instead. ([pypi.org/pypi/sweagent/json](https://pypi.org/pypi/sweagent/json), [swe-agent.com/latest/installation/source](https://swe-agent.com/latest/installation/source/))

## Beyond issue-fixing: EnIGMA for security research

A related sub-project, EnIGMA, extends the same ACI approach to offensive security / CTF challenges, adding "Interactive Agent Tools" for things like concurrent debugger and shell access, and the vendor reports it solved 13.5% of NYU CTF benchmark challenges, said to be over 3x the prior best agent on that benchmark. This is a vendor-reported figure from the docs, not independently corroborated here, and is a narrower research use case than the core issue-resolution tool. ([swe-agent.com/latest/background](https://swe-agent.com/latest/background/))

## SWE-agent price and terms

### Terms

- Free plan: Yes The documentation site publishes no plans, no rate card and no paid tier

The terms in full

SWE-agent is presented as an open-source project installed from source and run by the user.

Where these prices come from

[swe-agent.com](https://swe-agent.com/), checked 28 October 2026

### All plans and limits

| Plan | Price | Main limits |
| --- | --- | --- |
| SWE-agent | Free | None stated |

Read 28 October 2026 from [swe-agent.com](https://swe-agent.com/).

## What we checked on SWE-agent

How you build with it Yes

### Open source

MIT licence in its public repository

> MIT License

LICENSE in github.com/SWE-agent/SWE-agent [github.com/SWE-agent/SWE-agent/blob/mai…](https://github.com/SWE-agent/SWE-agent/blob/main/LICENSE) Checked by us, 15 November 2026

## SWE-agent alternatives

- [Hyper](https://agentsindex.ai/hyper) · The team behind Hyper runs this listing · Autonomous engineering agent that ships each delivery with server-run test evidence and a hard cost cap. · Free, then $20 a month Checked 20 Nov · Freemium Free trial · [Visit](https://agentsindex.ai/go/hyper)
  - MCP server: yes
  - API: yes
  - Open source: partly
  - Self-host: no
- SWE-agent and Hyper
  | SWE-agent | Free | 28 Oct |
  | --- | --- | --- |
  | [Hyper](https://agentsindex.ai/hyper) | Free, then $20 a month | 20 Nov |

## Questions about SWE-agent

- How much does SWE-agent cost?: SWE-agent is free to use. From swe-agent.com, checked 28 October 2026.
- Is SWE-agent open source, and can you host it yourself?: SWE-agent is open source. We checked github.com/SWE-agent/SWE-agent/blob/main/LICENSE ourselves on 15 November 2026. You can host SWE-agent yourself.
- What have we checked on SWE-agent?: 1 fact, under one heading: How you build with it.
- How do we check SWE-agent?: We hold 1 fact on SWE-agent, quoted from 2 pages. Facts last checked 15 November 2026. Price last checked 28 October 2026. Last change found 15 November 2026.

[How we check every listing](https://agentsindex.ai/methodology)

## Sources and changes

Last full check 28 October 2026

Sources 1

- Read 28 October 2026 · [swe-agent.com](https://swe-agent.com/) /

What changed 1

- 15 November 2026 What it does

Repository

- Licence: MIT
- Stars: 20,574
- Last push: 12 October 2026

## SWE-agent price history

We have read the price once so far, on 28 October 2026: free.

| Price | Plan | First seen | Last seen | Readings | Source |
| --- | --- | --- | --- | --- | --- |
| Free |   | 28 October 2026 | 28 October 2026 | 1 | [Pricing page, read 28 October 2026](https://swe-agent.com/) |

From our research on 28 October 2026. A date is when we read the page, not when the price changed.

## Is SWE-agent yours?

Free, and the page then carries the verified owner mark. You confirm it with an email at swe-agent.com. [Claim this listing](https://agentsindex.ai/claim/swe-agent?from=owner-line)

[Report an error](mailto:hello@agentsindex.ai?subject=Report%20an%20error%3A%20SWE-agent%20(swe-agent)&body=What%20is%20wrong%20on%20the%20page%2C%20and%20where%20on%20the%20product) if a fact is wrong.
