Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
PythonApache-2.0★ 26,111 stars⑂ 2,979 forkssince Nov 2019View on GitHub ↗
deepset-ai/haystack holds a health index of 100 out of 100, placing it in the Exceptional band. It scores highest on Vitality (100/100) and lowest on Engineering Quality (82/100). It was last updated today. 7 contributors account for most of its recent work.
100
overall / 100
Exceptional
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.
100
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
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 93 is calibrated to 100 on the published index scale (record calibration 2026-08-02).
Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25
Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40
No advisories left outstanding — no advisory carries a publication date
Inputs used
source
osv
advisories
0
affected_packages
0
assessed_packages
38
unassessed_packages
0
affected_by_severity
none
direct_affected_packages
0
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:haystack-ai@3.0.0 runtime dependency closure — what installing the published package pulls in — 38 packages. Reachability is not analyzed.
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.
API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20
MCP server
40/40
Runnable examples — examples, samples
Inputs used
example_dirs
examples, samples
has_mcp_signal
yes
api_schema_files
—
interfaces_expected_of
—
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto). Remaining weights renormalized.
Key facts
26,111GitHub stars
98contributors
1,716commits, last 12 months
0days since last push
100releases
7bus factor
65open issues
npm, PyPIpackage ecosystems
Data collection warnings
Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
First-time contributor figures cover 12 of 28 authors (cap 12)
More detail
Star and fork history 0 ★ / 2,979 ⇿
0Stars
2,979Forks
83Releases
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.
Major 1Minor 20Patch 20
Each point covers 2 days.
OpenSSF Scorecard 9.4 / 10
9.4aggregate
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).Scorecard v5.5.0 · 2026-08-05 02:56 UTC
Full resolved dependency set from the GitHub dependency graph: 21 direct and 3 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
Registry
Package
Version
Relation
npm
@docusaurus/core
^3.10.0
direct
npm
@docusaurus/faster
^3.10.0
direct
npm
@docusaurus/plugin-client-redirects
^3.10.0
direct
npm
@docusaurus/plugin-content-docs
^3.10.0
direct
npm
@docusaurus/plugin-ideal-image
^3.10.0
direct
npm
@docusaurus/preset-classic
^3.10.0
direct
npm
@mdx-js/react
^3.0.0
direct
npm
@types/turndown
^5.0.6
direct
npm
@vercel/node
^5.5.6
direct
npm
clsx
^2.0.0
direct
npm
docusaurus-plugin-generate-llms-txt
^0.0.1
direct
npm
prism-react-renderer
^2.3.0
direct
npm
react
^19.0.0
direct
npm
react-dom
^19.0.0
direct
npm
sharp
^0.35.0
direct
npm
turndown
^7.2.2
direct
npm
vercel
^58.0.0
direct
PyPI
openai
—
direct
PyPI
posthog
—
direct
PyPI
tenacity
—
direct
PyPI
typing-extensions
—
direct
npm
@docusaurus/module-type-aliases
^3.10.0
indirect
npm
@docusaurus/types
^3.10.0
indirect
PyPI
hatchling
—
indirect
Dependency advisories 0
Installing pypi:haystack-ai@3.0.0 pulls in 38 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.
No known advisories affect the assessed dependencies.
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.
Related records
Inspected repositories sharing catalogue tags or ecosystems with deepset-ai/haystack. Read them side by side →
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 v0.31.0 — full methodology · metrics wiki.
