Free
Free
Open-source agent documented for free local use; users supply their own model API credentials.
- Access
- Open-source agent documented for free local use; users supply their own model API credentials.
Mini SWE-Agent
● Identity checkedDeveloper Tools · Vendor site 2026-10-04
mini-SWE-agent is a minimal hundred-line Python coding agent from the SWE-agent team that solves software engineering tasks using only bash actions executed through subprocess calls. It supports many model providers via LiteLLM, runs in local or containerized environments, and targets researchers who want a simple, hackable agent baseline.
- Category
- Developer Tools
- Free access
- Open-source agent documented for free local use; users supply their own model API credentials.
- API access
- Documentation describes Python bindings and LiteLLM model integrations for programmatic agent runs.
Is Mini SWE-Agent right for you?
A good fit for
Researchers and developers benchmarking coding agents or needing a lightweight bash-only SWE baseline.
Before you choose
The project requires you to bring your own language-model accounts and infrastructure for sandboxed execution.
A 100-line agent that stays useful
mini-SWE-agent strips coding agents down to bash execution and linear trajectories so teams can benchmark models, debug prompts, and deploy sandboxes without complex tool schemas.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Minimal design | Docs describe roughly 100 lines of Python with bash-only actions and linear message history. | Facts sourced | 2026-10-04 |
| Benchmark performance | Homepage cites greater than 74% on SWE-bench Verified with faster startup than heavier agents. | Facts sourced | 2026-10-04 |
| Environments | Documentation lists local, Docker, Singularity, bubblewrap, and other sandbox backends. | Facts sourced | 2026-10-04 |
Understand the total cost
Mini SWE-Agent pricing & plans
Alternatives to Mini SWE-Agent
View all ↗
ConductorConductor runs parallel coding agents on Mac with optional Conductor Cloud sandboxes, multiplayer workspaces, mobile control, and an API. It orchestrates first-party Claude Code, Codex, Cursor, and OpenCode agents using your subscriptions and keys, with isolated microVMs for long-running cloud jobs.
Explore tool
Pre.devpre.dev is a long-horizon coding agent that plans, builds, and verifies software over extended runs in the browser or terminal. It connects to many SaaS tools, publishes previews, and sells separate RL coding tasks to AI labs through pre.dev Labs.
Explore tool
DevinDevin is Cognition’s autonomous software engineering agent that runs in the cloud or locally, tests in its own browser, and works toward merge-ready pull requests. Plans span individual coding quotas through team collaboration with Devin Cloud, DeepWiki, and enterprise controls.
Explore toolThe practical questions
Frequently asked questions
What is Mini SWE-Agent used for?
mini-SWE-agent is a minimal hundred-line Python coding agent from the SWE-agent team that solves software engineering tasks using only bash actions executed through subprocess calls. It supports many model providers via LiteLLM, runs in local or containerized environments, and targets researchers who want a simple, hackable agent baseline.
Does Mini SWE-Agent have a free plan?
Open-source agent documented for free local use; users supply their own model API credentials.. This record lists ongoing free access; check the plan limits before starting.
How much does Mini SWE-Agent cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Mini SWE-Agent through an API?
Documentation describes Python bindings and LiteLLM model integrations for programmatic agent runs.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
The project requires you to bring your own language-model accounts and infrastructure for sandboxed execution.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Identity and profile
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.