LightRAG
Website
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Is LightRAG safe? Strong public trust posture, backed by multiple independent signals.
Compare LightRAG
How does it stack up against its Memory & Knowledge neighbours?
Pick any agent to compare →In detail: LightRAG scores 84.4/100 (Grade A), ranked #101 of 1378 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 5.5/10; 53% of recent commits are signed; no published advisory affects its latest release (lightrag-hku); last pushed 2026-10-15. Every point is earned from checkable signals — never paid placement. How scoring works →
How LightRAG could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Raise the OSSF Scorecard from 5.5 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Pinned-Dependencies 0 +5.9 → 90.3 A · #1 of 51
- Sign every commit53% signed today +2.0 → 86.4 A · #6 of 51
Chain of custody
Scanners check what the code says. This traces who ships LightRAG 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.
-
Source Partly signed
github.com/HKUDS/LightRAG, MIT, last pushed 2026-10-15. 53% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 5.5/10 (scanned Oct 15, 2026). The checks that decide who can get a change released:
- Code Review2
- Branch Protection3
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 3CI-Tests 9CII-Best-Practices 0Code-Review 2Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 10Packaging 10Pinned-Dependencies 0SAST 0Security-Policy 10Signed-Releases -1Token-Permissions 0Vulnerabilities 0 -
Published packages Linked and attested
- PyPI lightrag-hku Source link points back to this repo Build provenance attested
-
What you install today No known advisories
Latest release checked: lightrag-hku 1.5.7. No published advisory affects it (OSV, checked 2026-10-17).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of LightRAG.
Evidence behind this score
Coverage A: 4 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions
Verify this score yourself
Every build re-issues LightRAG’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.
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 LightRAG compares in Memory & Knowledge
- #8 Hindsight 85.1 +0.7
- #9 Vespa 84.6 +0.2
- #10 LightRAG 84.4 this agent
- #11 agentmemory 76.3 −8.1
- #12 Qdrant 76.0 −8.4
Bars show each HVTrust score; the tick marks LightRAG’s 84.4.
Where the 84.4 comes from
HVTrust dimensions vs the Memory & Knowledge average
84.4 / 100 · 100.0% confidenceLightRAG Memory & Knowledge average (51 agents)
Quick Trust Read
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 A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
95.0 / 100Common questions about LightRAG
Does LightRAG publish package provenance?
Does LightRAG have an OpenSSF Scorecard?
Is LightRAG actively maintained?
What license does LightRAG use?
Are LightRAG's commits signed?
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.
AI agent surface
MCP, providers, tool surface
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 →
- database
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Maintain LightRAG?
For maintainers
HVTrust scores LightRAG 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.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/lightrag)
<a href="https://hvtracker.net/agents/lightrag"><img src="https://hvtracker.net/badge/lightrag.svg" alt="HVTrust"></a>
Other agents in Memory & Knowledge
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON