Letta

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Memory & Knowledge Python Grade C Listed Apache-2.0
61.8/100
Rank #299 of 1308
Compare Letta

How does it stack up against its Memory & Knowledge neighbours?

Pick any agent to compare →

Promising trust profile, but some evidence still deserves review.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade A · 4/5 signals
Last push
2026-08-23 · 2d ago
Recent change
Rank +3

Is Letta safe? Letta scores 61.8/100 (Grade C), ranked #299 of 1308 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.6/10; 3% of recent commits are signed; last pushed 2026-08-23. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Memory & Knowledge

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-08-24
Rank Moved
Rank rose 12 spots (#306 → #294)
2026-08-23
Rank Moved
Rank rose 12 spots (#318 → #306)
2026-08-22
Rank Moved
Rank rose 11 spots (#329 → #318)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 6.6/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
76.8
Activity sub-score · out of 100
#26

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C 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 →

Signals refreshed 2026-08-25 11:32 UTC · Repo last pushed 2 days ago

Rank Trend

2026-08-11 2026-08-25

Activity & Reach

Stars
24.4k
Forks
2.6k
Last Push
2026-08-23
2 days ago
Commits (4 wk)
5
Downloads (7d)
26,840
pypi
HN mentions (30d)
1
Open Issues
16
Rank Change
▼5
was #294

Analysis

HVTrust Dimensions vs Memory & Knowledge

61.8 / 100 · 100.0% confidence

Letta Memory & Knowledge average (44 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
8.4 / 25
1.6 below avg 10.0
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
1.3 below avg 12.1
Transparency50% declared license · 50% OSSF Scorecard
14.1 / 17
1.7 above avg 12.4
Maintenance60% last-push freshness · 40% commit activity
15.0 / 20
2.6 below avg 17.6
AdoptionLog-scaled stars · package downloads
16.4 / 20
2.8 above avg 13.6

Activity Inputs

76.8 / 100
StarsRepository reach
26.3 / 30
FreshnessLast push recency
24.7 / 25
ActivityRecent commits
9.7 / 25
CommunityFork signal
15.9 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
6.6 / 10
OpenSSF Scorecard · scanned Aug 25, 2026
Signed Commits
3%
of last 100 commits verified
Binary-Artifacts 10
Branch-Protection 5
CI-Tests 8
CII-Best-Practices 0
Code-Review 8
Contributors 10
Dangerous-Workflow 10
Dependency-Update-Tool 0
Fuzzing 0
License 10
Maintained 9
Packaging -1
Pinned-Dependencies 0
SAST 0
Security-Policy 10
Signed-Releases -1
Token-Permissions 10
Vulnerabilities 10

Is Letta safe?

Letta has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does Letta publish package provenance?
No published build provenance is currently detected for Letta. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Letta have an OpenSSF Scorecard?
Letta has an OpenSSF Scorecard score of 6.6/10. 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 Letta actively maintained?
Actively maintained. The repository was pushed to within the last 2 day(s).
What license does Letta use?
Letta ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Letta's commits signed?
3% of the last 100 commits to Letta 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.

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
high confidence
Implemented
Letta appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
10 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
  • database
  • search
Detailed evidence is not shown in the public view.
Package Provenance Drift
low confidence
Unknown
Package source metadata is missing or inconclusive
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

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
Rank 18HVTrust 3Score 1
2026-08-24
Rank Moved
Rank rose 12 spots (#306 → #294)
2026-08-23
Rank Moved
Rank rose 12 spots (#318 → #306)
2026-08-22
Rank Moved
Rank rose 11 spots (#329 → #318)
2026-08-19
Rank Moved
Rank dropped 19 spots (#310 → #329)
2026-08-17
Rank Moved
Rank rose 81 spots (#394 → #313)
2026-08-17
HVTrust Changed
HVTrust up 3.7pts (56.8 → 60.5)
2026-08-14
Rank Moved
Rank rose 11 spots (#401 → #390)
2026-08-12
Rank Moved
Rank rose 11 spots (#409 → #398)
2026-08-10
Rank Moved
Rank dropped 18 spots (#390 → #408)
2026-08-08
Rank Moved
Rank dropped 96 spots (#292 → #388)
2026-07-15
Rank Moved
Rank dropped 12 spots (#250 → #262)
2026-07-14
Rank Moved
Rank dropped 14 spots (#236 → #250)
2026-07-13
Rank Moved
Rank dropped 30 spots (#206 → #236)
2026-07-03
Rank Moved
Rank rose 11 spots (#195 → #184)
2026-06-26
Rank Moved
Rank rose 25 spots (#215 → #190)
2026-06-26
HVTrust Changed
HVTrust up 4.9pts (53.9 → 58.8)
2026-06-26
Activity Score Changed
Activity score up 12pts (61 → 73)
2026-06-24
Rank Moved
Rank dropped 25 spots (#188 → #213)
2026-06-23
Rank Moved
Rank dropped 12 spots (#176 → #188)
2026-06-18
Rank Moved
Rank dropped 13 spots (#143 → #156)
2026-06-01
Rank Moved
Rank dropped 15 spots (#102 → #117)
2026-05-29
HVTrust Changed
HVTrust up 9.9pts (42.8 → 52.7)

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 61.8 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/letta.svg)](https://hvtracker.net/agents/letta)
HTML:
<a href="https://hvtracker.net/agents/letta"><img src="https://hvtracker.net/badge/letta.svg" alt="HVTrust"></a>

Other agents in Memory & Knowledge

Data sources
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 v4.3 · Raw JSON