updated 2026-10-11 00:07 UTC

Haystack

Repository Website

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…

Agent Frameworks Python Listed Apache-2.0

Is Haystack safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 9.2 / 10
Provenance Attested
Signed commits 100%
Last push yesterday
Advisories None known
Compare Haystack

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →
Suggest a correction

In detail: Haystack scores 96.3/100 (Grade A), ranked #1 of 1371 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 9.2/10; 100% of recent commits are signed; no published advisory affects its latest release (haystack-ai); last pushed 2026-10-10. Every point is earned from checkable signals — never paid placement. How scoring works →

Chain of custody

Scanners check what the code says. This traces who ships Haystack and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Signed

    github.com/deepset-ai/haystack, Apache-2.0, last pushed 2026-10-10. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Strong

    OpenSSF Scorecard rates the repository's practices 9.2/10 (scanned Oct 10, 2026). The checks that decide who can get a change released:

    • Code Review10
    • Branch Protection8
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions10
    • Pinned Dependencies5
    All 14 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 8
    CII-Best-Practices 5
    Code-Review 10
    Dangerous-Workflow 10
    Fuzzing 10
    License 10
    Maintained 10
    Packaging 10
    Pinned-Dependencies 5
    SAST 8
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 10

  3. Published packages Linked and attested

    • PyPI haystack-ai Source link points back to this repo Build provenance attested

  4. What you install today No known advisories

    Latest release checked: haystack-ai 3.3.0. No published advisory affects it (OSV, checked 2026-10-10).

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Haystack.

Evidence behind this score

Coverage B: 3 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions (missing)

Verify this score yourself

Every build re-issues Haystack’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How Haystack compares in Agent Frameworks

  1. #1 Haystack 96.3 this agent
  2. #2 LangGraph 94.2 −2.1
  3. #3 OpenAI Agents SDK (JS) 94.1 −2.2
  4. #4 Vercel AI SDK 92.9 −3.4
  5. #5 OpenAI Agents SDK 91.4 −4.9

Bars show each HVTrust score; the tick marks Haystack’s 96.3.

Where the 96.3 comes from

HVTrust dimensions vs the Agent Frameworks average

96.3 / 100 · 100.0% confidence

Haystack Agent Frameworks average (129 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
24.0 / 25
14.3 above avg 9.7
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
6.4 above avg 11.6
Transparency50% declared license · 50% OSSF Scorecard
16.3 / 17
4.0 above avg 12.3
Maintenance60% last-push freshness · 40% commit activity
19.9 / 20
5.6 above avg 14.3
AdoptionLog-scaled stars · package downloads
17.5 / 20
6.3 above avg 11.2

Quick Trust Read

What Would Improve It
Improve adoption to lift the weakest part of the trust profile.
Maintainer Checklist
Keep signals current Trust posture is already in a healthy range. The main job is to keep provenance, maintenance, and public evidence fresh.
Compare with LangGraph Get email alerts for Haystack View Agent Frameworks Report missing data
92.9
Activity sub-score · out of 100
#1
In Agent Frameworks

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-11 00:07 UTC · Repo last pushed yesterday

Rank Trend

2026-09-29 2026-10-10

Activity & Reach

Stars
26.7k
Forks
3.3k
Last Push
2026-10-10
yesterday
Commits (4 wk)
260
Downloads (7d)
145,322
pypi
HN mentions (30d)
—
Open Issues
100
Rank Change
=
was #1

Analysis

Activity Inputs

92.9 / 100
StarsRepository reach
26.6 / 30
FreshnessLast push recency
24.9 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
16.3 / 20

Common questions about Haystack

Public supply-chain signals for Haystack are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but Haystack carries less obvious unverified-evidence risk than projects with thin signals.
Does Haystack publish package provenance?
Yes. Haystack's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does Haystack have an OpenSSF Scorecard?
Haystack has an OpenSSF Scorecard score of 9.2/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Haystack actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Haystack use?
Haystack ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Haystack's commits signed?
100% of the last 100 commits to Haystack are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Compare Haystack head-to-head

Haystack vs LangGraph → Haystack vs OpenAI Agents SDK (JS) → Haystack vs Vercel AI SDK →

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
1 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain Haystack?

For maintainers

HVTrust scores Haystack from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge
GitHub → Website → PyPI: haystack-ai

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 96.3 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/haystack.svg)](https://hvtracker.net/agents/haystack)
HTML:
<a href="https://hvtracker.net/agents/haystack"><img src="https://hvtracker.net/badge/haystack.svg" alt="HVTrust"></a>

Other agents in Agent Frameworks

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON