Letta
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Is Letta safe? Strong public trust posture, backed by multiple independent signals.
Compare Letta
How does it stack up against its Memory & Knowledge neighbours?
Pick any agent to compare →In detail: Letta scores 75.4/100 (Grade B), ranked #236 of 1371 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 6.3/10; 13% of recent commits are signed; no published advisory affects its latest release (letta); last pushed 2026-09-10. Every point is earned from checkable signals — never paid placement. How scoring works →
How Letta 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 6.3 to 9.0lowest checks: CII-Best-Practices 0, Dependency-Update-Tool 0, Fuzzing 0 +5.6 → 81.0 A · #11 of 49
- Sign every commit13% signed today +4.4 → 79.8 B · #11 of 49
Chain of custody
Scanners check what the code says. This traces who ships Letta 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/letta-ai/letta, Apache-2.0, last pushed 2026-09-10. 13% 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 6.3/10 (scanned Oct 3, 2026). The checks that decide who can get a change released:
- Code Review8
- Branch Protection5
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions10
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 5CI-Tests 6CII-Best-Practices 0Code-Review 8Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 0License 10Maintained 6Packaging -1Pinned-Dependencies 0SAST 0Security-Policy 10Signed-Releases -1Token-Permissions 10Vulnerabilities 10 -
Published packages Partly attested
- PyPI letta Source link points to letta-ai/letta-code, same owner Build provenance attested
-
What you install today No known advisories
Latest release checked: letta 0.34.4. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
- 2026-09-18 Package provenance attestation detected
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 Letta’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 Letta compares in Memory & Knowledge
- #11 Qdrant 76.1 +0.7
- #12 agentmemory 75.5 +0.1
- #13 Letta 75.4 this agent
- #14 FAISS 75.0 −0.4
- #15 Honcho 73.9 −1.5
Bars show each HVTrust score; the tick marks Letta’s 75.4.
Where the 75.4 comes from
HVTrust dimensions vs the Memory & Knowledge average
75.4 / 100 · 100.0% confidenceLetta Memory & Knowledge average (49 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 B 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
69.4 / 100Common questions about Letta
Does Letta publish package provenance?
Does Letta have an OpenSSF Scorecard?
Is Letta actively maintained?
What license does Letta use?
Are Letta'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 →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to Letta's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain Letta?
For maintainers
HVTrust scores Letta 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/letta)
<a href="https://hvtracker.net/agents/letta"><img src="https://hvtracker.net/badge/letta.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