{"adoption": {"forks": 99, "observed_at": "2026-08-28T04:04:54.059958+00:00", "stars": 1499}, "canonical_url": "https://ross.abutalabs.com/products/deep-swe", "card": {"archived": false, "artifact_type": "dataset", "description": "Measuring frontier coding agents on original, long-horizon engineering tasks", "domain": ["artificial-intelligence", "large-language-models", "developer-tools", "testing"], "enriched": true, "function": ["benchmarking", "testing", "agent-framework", "developer-tools"], "health_score": 78, "homepage": "https://deepswe.datacurve.ai/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["datacurve-ai/deep-swe"], "name": "datacurve-ai/deep-swe", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-06T20:05:06+00:00", "repo": "datacurve-ai/deep-swe", "stars": 1499, "tags": ["coding-agents", "benchmark", "llm-evaluation", "software-engineering-tasks", "leaderboard", "harbor-format", "ai-agents", "docker"], "topics": [], "urls": [], "use_cases": ["evaluate coding agents on realistic long-horizon engineering tasks", "compare frontier LLMs on software engineering benchmarks", "benchmark a new model against Claude, GPT, Gemini, and DeepSeek results", "run sandboxed agent evaluations with network allowlists", "measure pass@1 and cost efficiency of coding agents"], "what_it_is": "DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks drawn from active open-source repositories, used to measure frontier coding agents across TypeScript, Go, Python, JavaScript, and Rust. It ships with isolated Docker environments, program-based verifiers, and a public leaderboard of model results.", "when_to_avoid": ["you need a lightweight quick eval rather than full Docker-based runs", "you want short single-function coding tasks instead of long-horizon work", "you cannot run Docker or lack API access to frontier models"], "when_to_choose": ["you need a rigorous, verifiable benchmark for coding agents", "you want up-to-date leaderboard comparisons across many LLMs", "you need isolated, reproducible eval environments with held-out tests"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deep-swe", "repo": "datacurve-ai/deep-swe", "role": "main", "score": 57}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:54.059958+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:33:02.328193+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6bc496ee389e6a232f4ef48cb276f981584c4ddd9603339f8a9325c92c9c5ae7", "fetched_at": "2026-08-28T04:04:54.059958+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datacurve-ai/deep-swe"}, {"content_hash": "6a65a7f71b2aee379fb9f99fc755d75c887b32c01c1f62d597f2c5312d2305b1", "fetched_at": "2026-08-29T11:38:09.597746+00:00", "kind": "homepage", "missing": false, "url": "https://deepswe.datacurve.ai/"}, {"content_hash": "72cd8df7390eb0ceea4d56549a1dddb0362617a669b1452d551ac36dad6f7a9e", "fetched_at": "2026-08-29T11:38:09.607286+00:00", "kind": "site_page", "missing": false, "url": "https://deepswe.datacurve.ai/changelog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 7, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 110, "days_push": 27, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 57, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}