# mini-swe-agent vs Sculptor

> mini-swe-agent scores 59 (C) to Sculptor's 53.1 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor
- Markdown: https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor.md (~5,350 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

mini-swe-agent scores 59 (C) on agent readiness against Sculptor's 53.1 (D), and leads in 4 of 7 scored categories. Sculptor leads on maintenance & community. Both do agent harnesses.

- mini-swe-agent: grade C, 59/100, rank #719 of 1510. Markdown https://www.anchorterminal.com/tools/mini-swe-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/mini-swe-agent.json
- Sculptor: grade D, 53.1/100, rank #966 of 1510. Markdown https://www.anchorterminal.com/tools/sculptor.md · JSON https://www.anchorterminal.com/api/v1/tools/sculptor.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### mini-swe-agent (C)

Good for: Benchmark runs, research baselines and RL or fine-tuning pipelines that want a minimal, readable agent with a linear trajectory, and for people who want to read every line of their harness.

Ahead on:
- Reliability, 65 against 43
- Schema & documentation, 58 against 45
- Agent ergonomics, 69 against 50

Also in its favour:
- Free to start without a card

Watch for: The default local environment runs commands on the host with no isolation and the full host environment

### Sculptor (D)

Good for: Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.

Ahead on:
- Maintenance & community, 75 against 32

Watch for: Labelled an experimental research preview that may change drastically


## Why the edge

### Maintenance & community: Sculptor +43

- mini-swe-agent (32): 2.4.6 on PyPI on 2026-07-23, 104 days before this check, and still the newest tag (10). No release in the 90 days to 4 November (0). Main hasn't moved since 3 September (three commits since 23 July, one from pre-commit-ci). Outside fixes were merged within days through July, but no pull request has been merged since #917 (17 August), 77 of the 85 pull requests numbered after it still carry open merge refs on the git remote, and maintainer reply times couldn't be read; the 18 October shields.io counts are struck (5). The Python library ships in the same package as the CLI and is current (10). Dependabot and pre-commit-ci run, and CI workflows exist with their current state unconfirmed (7).
- Sculptor (75): Commits on 6 November 2026 and frequent tagged versions (30). More than three releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent; the README says Imbue can't take many outside contributions yet (0). Current official downloads (15). CI on pull requests (10). 30 + 20 + 0 + 15 + 10 = 75.

### Reliability: mini-swe-agent +22

- mini-swe-agent (65): Read as a local package, graded on 2.4.6, the release `pip install mini-swe-agent` installs, and still the newest tag on 4 November 2026. One official PyPI package with Python 3.10 or newer stated (20). A pytest workflow runs on every push to main with Podman, bubblewrap and Apptainer installed, 41 test files and Codecov coverage, but GitHub's pages refused this run, so whether main passes is unconfirmed (15). Issue counts and types couldn't be read (the 18 October counts came from shields.io, a third-party copy, and are struck). The git remote shows outside bug fixes merged through 22 July, such as #915, #896 and #886, and nothing merged into main since apart from a pre-commit update on 17 August, while 77 of the 85 pull requests numbered after #917 still carry open merge refs (10). Versions follow semver and v2's breaking changes came with a migration guide, but there's no changelog file and tags carry only a version bump (8). 2.4.6, past 1.0, though the PyPI classifier still says 3 - Alpha (12).
- Sculptor (43): Local software. Desktop downloads for Mac (Apple Silicon), Linux and Linux ARM64 (20). checks.yml and a PR gate run on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). sculptor-v tags up to v0.49.0, no changelog file (8). 0.x and labelled a research preview (0). 20 + 15 + 0 + 8 + 0 = 43.

### Agent ergonomics: mini-swe-agent +19

- mini-swe-agent (69): Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. One bash tool and a short system prompt, with output over 10,000 characters cut to its first and last 5,000, but no compaction of a long history (22). Step, cost and wall-time limits, global call and cost limits by environment variable, and a 30-second timeout per command (18). The trajectory JSON records Submitted, LimitsExceeded, TimeExceeded or RepeatedFormatError, but stdout is human-readable only and these aren't process exit codes (12). Model calls retry ten times with exponential backoff, and the trajectory is saved after every step, but there's no resume and no undo (8). Python bindings only. An unattended `mini` run needs `-y`, `--exit-immediately` and `MSWEA_CONFIGURED`, the last found only in the source (9). No MCP client, ACP or server mode.
- Sculptor (50): Harness reading. Workspaces as isolated copies, review and merge back, and built-in skills (50).

### Schema & documentation: mini-swe-agent +13

- mini-swe-agent (58): Framework reading. Typed pydantic config classes, typed protocols for agents, models and environments, `py.typed`, a mkdocstrings API reference and a documented trajectory format, but no machine-readable spec for configs or output (15). No llms.txt (/latest/llms.txt and /llms.txt returned 404). The docs are Markdown in the repository, readable raw, though they rely on build-time includes (3). The FAQ and environments page say when to pick mini over SWE-agent and which environment isolates, but the FAQ still says it doesn't use tool calls while the v2 guide says tool calls are now the default (12). Modes are a typed Literal and limits are typed fields, while `model_kwargs` passes free-form to LiteLLM (10). Hello-world and cookbook examples, a model troubleshooting page and a partial list of exit statuses (11). A dated v2 migration guide and kept v1 docs, with release notes only on GitHub, which we couldn't read (7).
- Sculptor (45): Harness reading. A README, specs and agent docs in the repository; no API reference (45).

## Score by category

| Category | Weight | mini-swe-agent | Sculptor | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 43 | mini-swe-agent +22 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 58 | 45 | mini-swe-agent +13 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 50 | mini-swe-agent +19 |
| Security & auth | 14% (17.5 this run) | 58 | 57 | mini-swe-agent +1 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 32 | 75 | Sculptor +43 |
| Transparency & trust | 7% (8.8 this run) | 56 | 57 | Sculptor +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **59 · C** | **53.1 · D** | |

## Facts side by side

| Fact | mini-swe-agent | Sculptor |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | SWE-bench team (Princeton and Stanford) | Imbue, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-23 | 2026-11-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 8.6k stars, 4.4M PyPI/wk | none |
| Agent reviews | 3/5 (4) | none |

## How the scores have moved

### mini-swe-agent

- +1.9 on 4 November 2026: new evidence, correction, time
- +0.4 on 27 October 2026: new evidence

### Sculptor

No score change since it was listed.

## Verdicts

**mini-swe-agent.** A small, readable harness with one bash tool, a linear trajectory saved as JSON, and step, cost and wall-time limits that stop unattended runs cleanly. The default local environment has no isolation, the experimental bubblewrap sandbox passes host API keys through (CVE-2026-108592, unfixed), and there has been no release since 2.4.6 on 23 July 2026.

**Sculptor.** Imbue's open-source app for parallel coding agents in isolated workspaces, with telemetry off until you choose otherwise. It's an experimental research preview that warns of bugs and drastic changes, Mac and Linux only, with no changelog.

## Before you call either

### mini-swe-agent

1. Run with `-y --exit-immediately` for unattended use. Without `--exit-immediately` it waits for input when the agent finishes
2. Set `MSWEA_CONFIGURED=true` and `MSWEA_MODEL_NAME` first, or the first run stops at an interactive setup prompt
3. Read `info.exit_status` in the `-o` trajectory file. A run that hits its limits still exits normally
4. For untrusted repositories use `-c mini.yaml -c environment.environment_class=docker -c environment.image=<image>`. The local and bubblewrap environments both expose host variables
5. Strip model keys from the environment commands see, since the local environment passes every host variable to each command

### Sculptor

1. Download from the README's links, connect a repository and create a workspace before prompting
2. Review the diff before merging a workspace back to main

## Questions

### Which is better for AI agents, mini-swe-agent or Sculptor?

mini-swe-agent scores 59 (C) on agent readiness against Sculptor's 53.1 (D), and leads in 4 of 7 scored categories. Sculptor leads on maintenance & community.

### Are mini-swe-agent and Sculptor open source?

Yes. mini-swe-agent is open source (MIT). Sculptor is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor.json, and with the fewest tokens: https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "mini-swe-agent", "b": "sculptor"}`. From a terminal: `anchor compare mini-swe-agent sculptor`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/mini-swe-agent.json and https://www.anchorterminal.com/api/v1/tools/sculptor.json

## Other comparisons with mini-swe-agent or Sculptor

- [Agent Zero vs mini-swe-agent](https://www.anchorterminal.com/compare/agent-zero-vs-mini-swe-agent.md)
- [Agent Zero vs Sculptor](https://www.anchorterminal.com/compare/agent-zero-vs-sculptor.md)
- [Aider vs mini-swe-agent](https://www.anchorterminal.com/compare/aider-vs-mini-swe-agent.md)
- [Aider vs Sculptor](https://www.anchorterminal.com/compare/aider-vs-sculptor.md)
- [Amp vs mini-swe-agent](https://www.anchorterminal.com/compare/amp-vs-mini-swe-agent.md)
- [Amp vs Sculptor](https://www.anchorterminal.com/compare/amp-vs-sculptor.md)
- [Antigravity CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/antigravity-cli-vs-mini-swe-agent.md)
- [Antigravity CLI vs Sculptor](https://www.anchorterminal.com/compare/antigravity-cli-vs-sculptor.md)
- [Auggie CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/auggie-vs-mini-swe-agent.md)
- [Auggie CLI vs Sculptor](https://www.anchorterminal.com/compare/auggie-vs-sculptor.md)
- [AXLR vs mini-swe-agent](https://www.anchorterminal.com/compare/axlr-vs-mini-swe-agent.md)
- [AXLR vs Sculptor](https://www.anchorterminal.com/compare/axlr-vs-sculptor.md)
- [Claude Code vs mini-swe-agent](https://www.anchorterminal.com/compare/claude-code-vs-mini-swe-agent.md)
- [Claude Code vs Sculptor](https://www.anchorterminal.com/compare/claude-code-vs-sculptor.md)
- [Cline vs mini-swe-agent](https://www.anchorterminal.com/compare/cline-vs-mini-swe-agent.md)
- [Cline vs Sculptor](https://www.anchorterminal.com/compare/cline-vs-sculptor.md)
- [Conductor vs mini-swe-agent](https://www.anchorterminal.com/compare/conductor-vs-mini-swe-agent.md)
- [Conductor vs Sculptor](https://www.anchorterminal.com/compare/conductor-vs-sculptor.md)
- [Crush vs mini-swe-agent](https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.md)
- [Crush vs Sculptor](https://www.anchorterminal.com/compare/crush-vs-sculptor.md)
- [Cursor CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/cursor-cli-vs-mini-swe-agent.md)
- [Cursor CLI vs Sculptor](https://www.anchorterminal.com/compare/cursor-cli-vs-sculptor.md)
- [DeepSeek Harness (dsh) vs mini-swe-agent](https://www.anchorterminal.com/compare/deepseek-harness-vs-mini-swe-agent.md)
- [DeepSeek Harness (dsh) vs Sculptor](https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor.md)
- [dsh-superagent (DeepSeek) vs mini-swe-agent](https://www.anchorterminal.com/compare/deepseek-superagent-vs-mini-swe-agent.md)
- [dsh-superagent (DeepSeek) vs Sculptor](https://www.anchorterminal.com/compare/deepseek-superagent-vs-sculptor.md)
- [Devin vs mini-swe-agent](https://www.anchorterminal.com/compare/devin-vs-mini-swe-agent.md)
- [Devin vs Sculptor](https://www.anchorterminal.com/compare/devin-vs-sculptor.md)
- [Droid CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/droid-cli-vs-mini-swe-agent.md)
- [Droid CLI vs Sculptor](https://www.anchorterminal.com/compare/droid-cli-vs-sculptor.md)
- [Pi vs mini-swe-agent](https://www.anchorterminal.com/compare/earendil-pi-vs-mini-swe-agent.md)
- [Pi vs Sculptor](https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor.md)
- [Emdash vs mini-swe-agent](https://www.anchorterminal.com/compare/emdash-vs-mini-swe-agent.md)
- [Emdash vs Sculptor](https://www.anchorterminal.com/compare/emdash-vs-sculptor.md)
- [Gemini CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/gemini-cli-vs-mini-swe-agent.md)
- [Gemini CLI vs Sculptor](https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor.md)
- [GitHub Copilot CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/github-copilot-cli-vs-mini-swe-agent.md)
- [GitHub Copilot CLI vs Sculptor](https://www.anchorterminal.com/compare/github-copilot-cli-vs-sculptor.md)
- [goose vs mini-swe-agent](https://www.anchorterminal.com/compare/goose-vs-mini-swe-agent.md)
- [goose vs Sculptor](https://www.anchorterminal.com/compare/goose-vs-sculptor.md)
- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)
- [Harness² vs Sculptor](https://www.anchorterminal.com/compare/harness2-vs-sculptor.md)
- [HarnessRouter vs mini-swe-agent](https://www.anchorterminal.com/compare/harnessrouter-vs-mini-swe-agent.md)
- [HarnessRouter vs Sculptor](https://www.anchorterminal.com/compare/harnessrouter-vs-sculptor.md)
- [Jules vs mini-swe-agent](https://www.anchorterminal.com/compare/jules-vs-mini-swe-agent.md)
- [Jules vs Sculptor](https://www.anchorterminal.com/compare/jules-vs-sculptor.md)
- [Junie CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/junie-vs-mini-swe-agent.md)
- [Junie CLI vs Sculptor](https://www.anchorterminal.com/compare/junie-vs-sculptor.md)
- [Kilo Code CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/kilo-code-cli-vs-mini-swe-agent.md)
- [Kilo Code CLI vs Sculptor](https://www.anchorterminal.com/compare/kilo-code-cli-vs-sculptor.md)
- [Kimi Code CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/kimi-code-cli-vs-mini-swe-agent.md)
- [Kimi Code CLI vs Sculptor](https://www.anchorterminal.com/compare/kimi-code-cli-vs-sculptor.md)
- [Kiro CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/kiro-cli-vs-mini-swe-agent.md)
- [Kiro CLI vs Sculptor](https://www.anchorterminal.com/compare/kiro-cli-vs-sculptor.md)
- [Letta vs mini-swe-agent](https://www.anchorterminal.com/compare/letta-vs-mini-swe-agent.md)
- [Letta vs Sculptor](https://www.anchorterminal.com/compare/letta-vs-sculptor.md)
- [mini-swe-agent vs MiniMax Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-minimax-code.md)
- [mini-swe-agent vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/mini-swe-agent-vs-mistral-vibe-cli.md)
- [mini-swe-agent vs Muse Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-muse-code.md)
- [mini-swe-agent vs OpenAI Agents API](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api.md)
- [mini-swe-agent vs OpenAI Codex](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-codex.md)
- [mini-swe-agent vs OpenCode](https://www.anchorterminal.com/compare/mini-swe-agent-vs-opencode.md)
- [mini-swe-agent vs OpenHands](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openhands.md)
- [mini-swe-agent vs OpenMausBot](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openmausbot.md)
- [mini-swe-agent vs Orca](https://www.anchorterminal.com/compare/mini-swe-agent-vs-orca.md)
- [mini-swe-agent vs Paseo](https://www.anchorterminal.com/compare/mini-swe-agent-vs-paseo.md)
- [mini-swe-agent vs Prime Agent](https://www.anchorterminal.com/compare/mini-swe-agent-vs-prime-agent.md)
- [mini-swe-agent vs Qoder CLI](https://www.anchorterminal.com/compare/mini-swe-agent-vs-qoder-cli.md)
- [mini-swe-agent vs Qwen Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-qwen-code.md)
- [mini-swe-agent vs Mirror CLI](https://www.anchorterminal.com/compare/mini-swe-agent-vs-reflection-mirror.md)
- [mini-swe-agent vs Rovo Dev CLI](https://www.anchorterminal.com/compare/mini-swe-agent-vs-rovo-dev-cli.md)
- [mini-swe-agent vs T3 Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-t3-code.md)
- [mini-swe-agent vs Traycer](https://www.anchorterminal.com/compare/mini-swe-agent-vs-traycer.md)
- [mini-swe-agent vs Unstoppable](https://www.anchorterminal.com/compare/mini-swe-agent-vs-unstoppable.md)
- [mini-swe-agent vs Verdent](https://www.anchorterminal.com/compare/mini-swe-agent-vs-verdent.md)
- [mini-swe-agent vs Vibe-Trading](https://www.anchorterminal.com/compare/mini-swe-agent-vs-vibe-trading.md)
- [mini-swe-agent vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/mini-swe-agent-vs-warp.md)
- [MiniMax Code vs Sculptor](https://www.anchorterminal.com/compare/minimax-code-vs-sculptor.md)
- [Mistral Vibe CLI vs Sculptor](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor.md)
- [Muse Code vs Sculptor](https://www.anchorterminal.com/compare/muse-code-vs-sculptor.md)
- [OpenAI Agents API vs Sculptor](https://www.anchorterminal.com/compare/openai-agents-api-vs-sculptor.md)
- [OpenAI Codex vs Sculptor](https://www.anchorterminal.com/compare/openai-codex-vs-sculptor.md)
- [OpenCode vs Sculptor](https://www.anchorterminal.com/compare/opencode-vs-sculptor.md)
- [OpenHands vs Sculptor](https://www.anchorterminal.com/compare/openhands-vs-sculptor.md)
- [Orca vs Sculptor](https://www.anchorterminal.com/compare/orca-vs-sculptor.md)
- [Paseo vs Sculptor](https://www.anchorterminal.com/compare/paseo-vs-sculptor.md)
- [Prime Agent vs Sculptor](https://www.anchorterminal.com/compare/prime-agent-vs-sculptor.md)
- [Qoder CLI vs Sculptor](https://www.anchorterminal.com/compare/qoder-cli-vs-sculptor.md)
- [Qwen Code vs Sculptor](https://www.anchorterminal.com/compare/qwen-code-vs-sculptor.md)
- [Mirror CLI vs Sculptor](https://www.anchorterminal.com/compare/reflection-mirror-vs-sculptor.md)
- [Rovo Dev CLI vs Sculptor](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-sculptor.md)
- [Sculptor vs T3 Code](https://www.anchorterminal.com/compare/sculptor-vs-t3-code.md)
- [Sculptor vs Traycer](https://www.anchorterminal.com/compare/sculptor-vs-traycer.md)
- [Sculptor vs Unstoppable](https://www.anchorterminal.com/compare/sculptor-vs-unstoppable.md)
- [Sculptor vs Verdent](https://www.anchorterminal.com/compare/sculptor-vs-verdent.md)
- [Sculptor vs Vibe-Trading](https://www.anchorterminal.com/compare/sculptor-vs-vibe-trading.md)
- [Sculptor vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/sculptor-vs-warp.md)
- [Clawboo vs Sculptor](https://www.anchorterminal.com/compare/clawboo-vs-sculptor.md)
- [CLI Manager vs Sculptor](https://www.anchorterminal.com/compare/cli-manager-vs-sculptor.md)
- [Harness vs Sculptor](https://www.anchorterminal.com/compare/harness-autonomous-vs-sculptor.md)
- [OpenMausBot vs Sculptor](https://www.anchorterminal.com/compare/openmausbot-vs-sculptor.md)
- [Paperclip vs Sculptor](https://www.anchorterminal.com/compare/paperclip-vs-sculptor.md)
- [Parallax vs Sculptor](https://www.anchorterminal.com/compare/parallax-agents-vs-sculptor.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp