FoundationAgents / MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
FoundationAgents/MetaGPT holds a health index of 69 out of 100, placing it in the Good band. It scores highest on Engineering Quality (86/100) and lowest on Vitality (34/100). It was last updated 240 days ago. 4 contributors account for most of its recent work.
Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
The weighted overall 62 is calibrated to 69 on the published index scale (record calibration 2026-08-02).
Ownership
This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish | Tags |
|---|---|---|---|---|---|---|
| PyPI | metagptpoints to another repo — not scored | 0.8.2 | 7,144 | 30 | 558 days ago | metagptmulti-agentmulti-roleprogramminggptllmmetaprogramming |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
Development activity
How it's scored
| 3.6/36 | Push recency — last push 240 days ago |
| 2.1/36 | Commit cadence — 3/52 weeks with commits |
| 5.4/18 | Commit volume — 3 commits in the last year |
| 0/10 | OpenSSF Scorecard: Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
Inputs used
| commits_last_year | 3 |
| human_commit_share | 1 |
| days_since_last_push | 240 |
| active_weeks_last_year | 3 |
Release discipline
How it's scored
| 27/27 | Ships releases — 22 releases published |
| 7.2/36 | Release recency — latest release 558 days ago |
| 27/27 | Release cadence — a release every ~43.8 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 22 |
| latest_release_tag | v0.8.2 |
| releases_from_tags | no |
| days_since_latest_release | 558 |
| mean_days_between_releases | 43.8 |
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
Popularity & adoption
How it's scored
| 60/60 | Stars — 70,492 stars |
| 25/25 | Forks — 8,959 forks |
| 15/15 | Watchers — 921 watchers |
Inputs used
| forks | 8,959 |
| stars | 70,492 |
| watchers | 921 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
How it's scored
| 22.5/22.5 | README |
| 22.5/22.5 | License — recognized license (MIT) |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 6.3/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| readme_badges | 3 |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| readme_badge_services | shields.io |
| has_pull_request_template | yes |
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
Maintainer resilience (bus factor)
How it's scored
| 43.2/54 | Bus factor — 4 contributor(s) cover half of all commits |
| 18.2/22.5 | Commit distribution — top contributor authored 19% of commits |
| 13.5/13.5 | Contributor breadth — 100 contributors |
| 10/10 | OpenSSF Scorecard: Contributors — project has 28 contributing companies or organizations |
Inputs used
| bus_factor | 4 |
| contributors_sampled | 100 |
| top_contributor_share | 0.19 |
How it's scored
| 41.5/42 | Issue resolution — 99% of issues closed |
| 20.9/30 | PR acceptance — 673/966 decided PRs merged |
| 0/13 | Newcomer PR acceptance — 0/1 first-time contributors' PRs merged in 30d |
| 7.5/15 | OpenSSF Scorecard: Code-Review — Found 6/11 approved changesets -- score normalized to 5 |
Inputs used
| merged_prs | 673 |
| open_issues | 11 |
| closed_issues | 967 |
| prs_merged_7d | 0 |
| prs_decided_7d | 0 |
| prs_merged_30d | 0 |
| prs_decided_30d | 1 |
| issue_closed_ratio | 0.989 |
| closed_unmerged_prs | 293 |
| first_time_authors_30d | 1 |
| first_time_prs_merged_30d | 0 |
| first_time_prs_decided_30d | 1 |
Ownership & stewardship
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 0/20 | Verified domain |
| 21.9/25 | Owner reach — 1,114 followers of FoundationAgents |
| 13.3/25 | Track record — 23 public repos, account ~1 yr old |
Inputs used
| followers | 1,114 |
| owner_type | Organization |
| is_verified | no |
| owner_login | FoundationAgents |
| public_repos | 23 |
| account_age_days | 589 |
Engineering Quality
Are baseline engineering and documentation practices in place?
Engineering practices
How it's scored
| 24/24 | CI workflows — 5 workflow(s) |
| 24/24 | Tests present |
| 16/16 | Linter config — .pylintrc, ruff.toml |
| 9.6/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 2/20 | OpenSSF Scorecard: CI-Tests — 1 out of 9 merged PRs checked by a CI test -- score normalized to 1 |
Inputs used
| has_ci | yes |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | yes |
| has_precommit_config | yes |
Documentation
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 15/15 | Documentation / homepage site — https://atoms.dev/ |
| 10/10 | Repository description |
| 10/10 | Topics — 5 topics |
| 10/10 | Wiki |
Inputs used
| topics | agent, gpt, llm, metagpt, multi-agent |
| has_wiki | yes |
| homepage | https://atoms.dev/ |
| docs_site | https://atoms.dev/ |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
Security posture
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 0.2/2.5 | CI-Tests — 1 out of 9 merged PRs checked by a CI test -- score normalized to 1 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 3.8/7.5 | Code-Review — Found 6/11 approved changesets -- score normalized to 5 |
| 2.5/2.5 | Contributors — project has 28 contributing companies or organizations |
| 0/10 | Dangerous-Workflow — dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | License — license file detected |
| 0/7.5 | Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
| 0/5 | Packaging — no data |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 5/5 | Security-Policy — security policy file detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 84 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 2.3 |
Dependency advisories
How it's scored
| 35/35 | Direct dependencies free of known advisories — no direct dependency carries a known advisory |
| 0/25 | Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope |
| 0/40 | No advisories left outstanding — no advisory carries a publication date |
Inputs used
| source | osv |
| advisories | 150 |
| affected_packages | 7 |
| assessed_packages | 43 |
| unassessed_packages | 58 |
| affected_by_severity | critical 4, high 1, moderate 1, low 1 |
| direct_affected_packages | 0 |
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.
Agent context & guidance
How it's scored
| 0/45 | Agent instructions — no CLAUDE.md / AGENTS.md / editor rules |
| 15/15 | Machine-readable docs (llms.txt) — llms.txt served by the project website (https://atoms.dev/llms.txt) |
| 16/40 | Legible commit history — 30 of 100 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | yes |
| llms_txt_url | https://atoms.dev/llms.txt |
| legible_history_share | 0.3 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Verify loop (build / test / typecheck)
How it's scored
| 0/18 | One-command bootstrap |
| 22/22 | Automated tests |
| 11/11 | Lint / format config — .pylintrc, ruff.toml |
| 11/11 | Static type checking — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/tsconfig.json |
| 10/10 | Reproducible environment — devcontainer, Dockerfile |
| 0/10 | Demonstrated agent practice — no agent-authored commits among the last 100 |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | — |
| has_dockerfile | yes |
| typed_language | no |
| bootstrap_files | — |
| has_devcontainer | yes |
| has_linter_config | yes |
| typecheck_configs | metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/tsconfig.json |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Code legibility for models
How it's scored
| 27/45 | Type-checkable code — Python with type-check config (metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/tsconfig.json) |
| 55/55 | Manageable file sizes — 0/913 source files over 60KB |
Inputs used
| primary_language | Python |
| largest_source_bytes | 47,784 |
| source_files_sampled | 913 |
| oversized_source_files | 0 |
Machine-readable interfaces
How it's scored
| 40/40 | API schema (OpenAPI/GraphQL/proto) — docs/.well-known/openapi.yaml |
| 0/20 | MCP server |
| 40/40 | Runnable examples — examples |
Inputs used
| example_dirs | examples |
| has_mcp_signal | no |
| api_schema_files | docs/.well-known/openapi.yaml |
| interfaces_expected_of | network-service |
Key facts
Data collection warnings
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- pypi package 'metagpt' points at a different repository (https://github.com/geekan/MetaGPT); excluded from ecosystem scoring
More detail
Star and fork history 0 ★ / 8,959 ⇿
When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.
Only the most recent history is shown — this repository exceeds the collection window, so the earliest history is not captured.
OpenSSF Scorecard 2.3 / 10
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| 1 | CI-Tests | 1 out of 9 merged PRs checked by a CI test -- score normalized to 1 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 5 | Code-Review | Found 6/11 approved changesets -- score normalized to 5 |
| 10 | Contributors | project has 28 contributing companies or organizations |
| 0 | Dangerous-Workflow | dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 0 | Maintained | 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
| n/a | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 10 | Security-Policy | security policy file detected |
| n/a | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 84 existing vulnerabilities detected |
All dependencies 101
Full resolved dependency set from the GitHub dependency graph: 0 direct and 101 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
| Registry | Package | Version | Relation |
|---|---|---|---|
| npm | @types/node | ^18.6.4 | indirect |
| npm | body-parser | ^1.20.2 | indirect |
| npm | express | ^4.18.2 | indirect |
| npm | graceful-fs | ^4.2.11 | indirect |
| npm | magic-string | ^0.30.0 | indirect |
| npm | minecraft-data | ^3.31.0 | indirect |
| npm | minecrafthawkeye | ^1.3.6 | indirect |
| npm | mineflayer | ^4.0.0 | indirect |
| npm | mineflayer | ^4.8.1 | indirect |
| npm | mineflayer-pathfinder | ^2.1.1 | indirect |
| npm | mineflayer-pathfinder | ^2.4.2 | indirect |
| npm | mineflayer-pvp | ^1.3.2 | indirect |
| npm | mineflayer-tool | ^1.1.0 | indirect |
| npm | mineflayer-tool | ^1.2.0 | indirect |
| npm | mocha | ^10.2.0 | indirect |
| npm | prettier | 2.8.5 | indirect |
| npm | prismarine-biome | ^1.3.0 | indirect |
| npm | prismarine-block | 1.16.3 | indirect |
| npm | prismarine-entity | ^2.2.0 | indirect |
| npm | prismarine-item | ^1.12.1 | indirect |
| npm | prismarine-nbt | ^2.2.1 | indirect |
| npm | prismarine-recipe | ^1.3.1 | indirect |
| npm | prismarine-viewer | ^1.24.0 | indirect |
| npm | require-self | ^0.2.3 | indirect |
| npm | ts-standard | ^11.0.0 | indirect |
| npm | typescript | ^4.1.3 | indirect |
| npm | typescript | ^4.9.5 | indirect |
| npm | vec3 | ^0.1.8 | indirect |
| PyPI | aiofiles | 23.2.1 | indirect |
| PyPI | aiohttp | 3.8.6 | indirect |
| PyPI | anthropic | 0.47.2 | indirect |
| PyPI | anytree | — | indirect |
| PyPI | beautifulsoup4 | 4.12.3 | indirect |
| PyPI | boto3 | — | indirect |
| PyPI | catboost | — | indirect |
| PyPI | channels | 4.0.0 | indirect |
| PyPI | curl-cffi | — | indirect |
| PyPI | dashscope | — | indirect |
| PyPI | faiss-cpu | 1.7.4 | indirect |
| PyPI | fire | 0.4.0 | indirect |
| PyPI | fsspec | — | indirect |
| PyPI | gitignore-parser | 0.1.9 | indirect |
| PyPI | gitpython | 3.1.40 | indirect |
| PyPI | google-generativeai | 0.4.1 | indirect |
| PyPI | grep-ast | — | indirect |
| PyPI | grpcio | — | indirect |
| PyPI | grpcio-status | — | indirect |
| PyPI | grpcio-tools | — | indirect |
| PyPI | gymnasium | 0.29.1 | indirect |
| PyPI | htmlmin | — | indirect |
| PyPI | httplib2 | — | indirect |
| PyPI | httpx | 0.28.1 | indirect |
| PyPI | ipykernel | 6.27.1 | indirect |
| PyPI | ipython | 8.17.2 | indirect |
| PyPI | ipywidgets | 8.1.1 | indirect |
| PyPI | jieba | 0.42.1 | indirect |
| PyPI | lancedb | 0.4.0 | indirect |
| PyPI | libcst | 1.0.1 | indirect |
| PyPI | lightgbm | — | indirect |
| PyPI | loguru | 0.6.0 | indirect |
| PyPI | meilisearch | 0.21.0 | indirect |
| PyPI | nbclient | 0.9.0 | indirect |
| PyPI | nbformat | 5.9.2 | indirect |
| PyPI | networkx | — | indirect |
| PyPI | numpy | — | indirect |
| PyPI | openai | — | indirect |
| PyPI | opencv-python | 4.6.0.66 | indirect |
| PyPI | openml | 0.14.2 | indirect |
| PyPI | openpyxl | — | indirect |
| PyPI | pandas | 2.1.1 | indirect |
| PyPI | pillow | — | indirect |
| PyPI | pydantic | — | indirect |
| PyPI | pygithub | — | indirect |
| PyPI | pylint | — | indirect |
| PyPI | pyshine | 0.0.9 | indirect |
| PyPI | python-docx | 0.8.11 | indirect |
| PyPI | pyyaml | 6.0.1 | indirect |
| PyPI | qdrant-client | 1.7.0 | indirect |
| PyPI | qianfan | — | indirect |
| PyPI | rank-bm25 | 0.2.2 | indirect |
| PyPI | requests | — | indirect |
| PyPI | rich | 13.6.0 | indirect |
| PyPI | scikit-learn | 1.3.2 | indirect |
| PyPI | semantic-kernel | 0.4.3.dev0 | indirect |
| PyPI | setuptools | — | indirect |
| PyPI | socksio | — | indirect |
| PyPI | spark-ai-python | — | indirect |
| PyPI | ta | 0.10.2 | indirect |
| PyPI | tenacity | 8.2.3 | indirect |
| PyPI | tiktoken | 0.7.0 | indirect |
| PyPI | tqdm | 4.66.2 | indirect |
| PyPI | tree-sitter | — | indirect |
| PyPI | tree-sitter-python | — | indirect |
| PyPI | typer | 0.9.0 | indirect |
| PyPI | typing-extensions | 4.11.0 | indirect |
| PyPI | typing-inspect | 0.8.0 | indirect |
| PyPI | websocket-client | — | indirect |
| PyPI | websockets | — | indirect |
| PyPI | wrapt | 1.15.0 | indirect |
| PyPI | xgboost | — | indirect |
| PyPI | zhipuai | — | indirect |
Dependency advisories 7
This repository publishes no package the index resolves, so its own dependency graph was assessed — 43 packages, which also include development and test pins that never ship: 7 carry known advisories, of which 0 are direct. 58 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list.
| Package | Version | Relation | Severity | Advisories | Fixed in |
|---|---|---|---|---|---|
| aiohttp | 3.8.6 | indirect | critical | 80 | 3.14.3 |
| gitpython | 3.1.40 | indirect | critical | 58 | 3.1.60 |
| qdrant-client | 1.7.0 | indirect | critical | 2 | 1.9.0 |
| semantic-kernel | 0.4.3.dev0 | indirect | critical | 4 | 1.71.0 |
| opencv-python | 4.6.0.66 | indirect | high | 2 | 4.8.1.78 |
| scikit-learn | 1.3.2 | indirect | moderate | 2 | 1.5.0 |
| tqdm | 4.66.2 | indirect | low | 2 | 4.66.3 |
An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.
Raw JSON report machine-readable
Feedback
Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.
Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.34.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — PyPI.