Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Coding / SWE-agent
◉AgentCodingFree

SWE-agent

Princeton's autonomous agent that resolves real GitHub issues end-to-end using a custom agent-computer interface.

@ai-supply
Installs376k
⟳ upstream v1.1.0 · updated 1y ago
↗ Source repository
← More CodingCoding leaderboard →How we grade security →Source ↗
✓ Grade A · 100/100 · SafeSecurity assessment
✓No compromise signals18capabilities surfaced8of 20 OWASP controls clear
External endpoints declaredExternal endpoints declaredSuspicious code patternsExternal endpoints declared
scanned 17d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

SWE-agent

SWE-agent from Princeton NLP turns any LLM into a software engineering agent capable of finding and fixing bugs in real-world GitHub repositories. It uses a carefully designed Agent-Computer Interface (ACI) that gives the model specialised commands for navigating codebases — dramatically improving performance over raw tool-use.

Key Features

  • Agent-Computer Interface: custom shell commands (search_file, view_file, edit_file) optimised for LLM code navigation
  • SWE-bench compatible: benchmarked on the full SWE-bench Verified dataset; reproducible evaluation scripts included
  • Multi-model: GPT-4o, Claude, Gemini, and any LiteLLM endpoint
  • Batch mode: run the agent over a dataset of issues in parallel for evaluation
  • Web UI: interactive traj viewer to replay and debug agent trajectories step-by-step
  • Extensible: plug in custom tools, filters, and cost controls

Quick Start

pip install sweagent

# Fix a GitHub issue
swe-agent run \
  --model_name claude-sonnet-4-5 \
  --data_path https://github.com/owner/repo/issues/42 \
  --repo_path /path/to/local/repo
npx ai-supply add swe-agent-github-issue-solver

Curated mirror of the open-source SWE-agent (MIT). Get it from the source.

Rating rank
#1
of 27 in Coding
Install rank
#5
of 27 in Coding
Security score
100/100 · A
safe
Security rank
#1
of 27 in Coding
Installs
376k
cat avg 157k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Coding leaderboard →
✓ Security: Safe · 100100/100 · grade Ascanned 17d ago
✓ no compromise signals18 risk-surface · 7/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · high confidence (static)
Tools (1)
end_of_edit
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → www.contributor-covenant.org, docs.github.com, swe-bench.slack.com, astral.sh, discord.gg, swe-agent.com, img.shields.io, arxiv.org +32

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · SWE-agent-SWE-agent-1132b3e/config/benchmarks/250212_sweagent_heavy_sbl.yaml (CWE-77)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — pipe-to-shell install · SWE-agent-SWE-agent-1132b3e/.github/workflows/build-docs.yaml (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · SWE-agent-SWE-agent-1132b3e/sweagent/inspector/fileViewer.js (CWE-95)risk surface
•Suspicious code patterns — OS command execution · SWE-agent-SWE-agent-1132b3e/sweagent/run/hooks/apply_patch.py (CWE-78)risk surface
•Suspicious code patterns — environment/secret exfiltration · SWE-agent-SWE-agent-1132b3e/tests/test_swesmith.py (CWE-200)risk surface
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · SWE-agent-SWE-agent-1132b3e/.devcontainer/bashrc_epilog.shrisk surface
•External endpoints declared — 2 distinct host(s) · SWE-agent-SWE-agent-1132b3e/.github/CODE_OF_CONDUCT.mdrisk surface
•External endpoints declared — 3 distinct host(s) · SWE-agent-SWE-agent-1132b3e/CONTRIBUTING.mdrisk surface
•External endpoints declared — 15 distinct host(s) · SWE-agent-SWE-agent-1132b3e/README.mdrisk surface
•External endpoints declared — 5 distinct host(s) · SWE-agent-SWE-agent-1132b3e/docs/background/index.mdrisk surface
•External endpoints declared — 7 distinct host(s) · SWE-agent-SWE-agent-1132b3e/docs/index.mdrisk surface
•External endpoints declared — 4 distinct host(s) · SWE-agent-SWE-agent-1132b3e/docs/installation/source.mdrisk surface
•External endpoints declared — 6 distinct host(s) · SWE-agent-SWE-agent-1132b3e/mlc_config.jsonrisk surface
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · SWE-agent-SWE-agent-1132b3e/sweagent/environment/repo.py (CWE-272)risk surface
⚠LLM07System Prompt Leakagemedium
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/swe-bench-dev-easy.json (CWE-200)risk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · SWE-agent-SWE-agent-1132b3e/docs/usage/memory_sentinel.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM02Sensitive Information DisclosurePassed
✓LLM03Supply ChainPassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · SWE-agent-SWE-agent-1132b3e/config/benchmarks/250212_sweagent_heavy_sbl.yaml (CWE-77)risk surface
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — pipe-to-shell install · SWE-agent-SWE-agent-1132b3e/.github/workflows/build-docs.yaml (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · SWE-agent-SWE-agent-1132b3e/sweagent/inspector/fileViewer.js (CWE-95)risk surface
•Suspicious code patterns — OS command execution · SWE-agent-SWE-agent-1132b3e/sweagent/run/hooks/apply_patch.py (CWE-78)risk surface
•Suspicious code patterns — environment/secret exfiltration · SWE-agent-SWE-agent-1132b3e/tests/test_swesmith.py (CWE-200)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML06AI Supply ChainPassed
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (15) · hygiene / uncategorized
•Unrecognized file type — '.mdc' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/.cursor/rules/general.mdcrisk surface
•Unrecognized file type — '.cfg' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/.devcontainer/sample_keys.cfgrisk surface
•Unrecognized file type — '.git-blame-ignore-revs' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/.git-blame-ignore-revsrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/LICENSErisk surface
•Unrecognized file type — '.log' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/docs/usage/coding_challenge_output.logrisk surface
•Unrecognized file type — '.c' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/ctf/crypto/Katy/customrandom.crisk surface
•Unrecognized file type — '.cpp' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/ctf/rev/rock/rock.cpprisk surface
•Unrecognized file type — '.conf' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/ctf/web/i_got_id_demo/000-default.confrisk surface
•Unrecognized file type — '.pl' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/ctf/web/i_got_id_demo/cgi/file.plrisk surface
•Suspicious network references — suspicious TLD (14 URLs) · SWE-agent-SWE-agent-1132b3e/tests/test_data/data_sources/swe-bench-dev-easy.jsonrisk surface
•Unrecognized file type — '.traj' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/trajectories/gpt4__swe-agent-test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/6e44b9__sweagenttestrepo-1c2844.trajrisk surface
•Possible obfuscation — very long lines paired with a decode/execute sink · SWE-agent-SWE-agent-1132b3e/tests/test_data/trajectories/gpt4__swe-agent__test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/swe-agent__test-repo-i1.traj (CWE-506)risk surface
•Unrecognized file type — '.jsonl' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/all_preds.jsonlrisk surface
•Unrecognized file type — '.patch' is not on the allowlist · SWE-agent-SWE-agent-1132b3e/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/patches/pydicom__pydicom-1458.patchrisk surface
✔ verified source · pinned SWE-agent-SWE-agent-1132b3e
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/swe-agent-github-issue-solver/check). Click a policy:

Consume SWE-agent programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/swe-agent-github-issue-solver

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/swe-agent-github-issue-solver/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add swe-agent-github-issue-solver

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/swe-agent-github-issue-solver/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "swe-agent-github-issue-solver" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1001mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy