Read 2026-11-03
letta-ai/letta: technical due diligence, read from its repository
What Borehole read in letta-ai/letta's code and history at 8816d3a: its licence, security advisories, releases, review practice, tests, dependencies and operations. Every finding cites the file and line it rests on. The full report also covers the team and asks the questions the code cannot answer.
| Dimension | Rating |
|---|---|
| Architecture & Codebase — including AI provenance | not assessable |
| Engineering Process & SDLC Maturity | strong |
| Product & Engineering Maturity | not assessable |
| Security & Reliability Posture | strong |
| Observability & Operations | not assessable |
| Fit with the Acquirer | not assessable |
What the repository says
AI_POLICY.md:1: states a policy on AI-generated contributions
Architecture & Codebase — including AI provenance
not assessableNot rated: only 5 of 11 checks could reach a conclusion here; the rest do not apply to this repository or could not read it.
Engineering Process & SDLC Maturity
strongNo finding.
Product & Engineering Maturity
not assessableNot rated: only 8 of 19 checks could reach a conclusion here; the rest do not apply to this repository or could not read it.
Security & Reliability Posture
strong1 credential-shaped string exists in the history
adequateMatches for private key block were committed at some point across 7,073 commits examined. The files that held them are no longer in the working tree — but removal from a file is not removal from the history, and the history is what transfers with the asset. What matters is whether each was rotated after it was committed. The code cannot tell whether any of them is live, and that decides whether this matters: none sits in production configuration, and none is in a format its provider keeps for live keys. Is any of these live? Show that each was rotated after it was committed, and when.
| private key block pattern added here |
5 advisories against this project in the last 24 months, 4 high or critical
adequateThe newest was published on 2026-10-20. A project that publishes advisories is telling its users about its fixes, and the count and pace say how much security work it carries. Whether 4 of them are fixed in the code you ship could not be told from this history: its version is only known to be at least 0.16.8. Answer lives in: the release you run, set against each fixed version. The record is incomplete: NVD: 3 records name letta with nothing tying them to this repository (CVE-2026-18990, CVE-2026-4964, CVE-2026-4965).
| 2026-10-20: CVE-2026-77936 (critical): Letta through 0.16.8 ships a compose.yaml that does not enable LETTA_SERVER_SECURE, so the password middleware is never added and all API routes are unauthentic |
| 2026-10-20: CVE-2026-77937 (high): Letta through 0.16.8 contains an authentication bypass vulnerability that allows API callers to impersonate other users by supplying a self-asserted user_id HTT |
| 2026-10-20: CVE-2026-77938 (high): Letta through 0.16.8 contains an information disclosure vulnerability that allows users running tools to read server secrets because LocalSandbox subprocesses i |
| 2025-07-22: CVE-2025-51482 (high): Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Pytho |
| 2025-06-16: CVE-2025-6101 (low): A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function function_message of the file letta/letta/interface |
Observability & Operations
not assessableNot rated: only 3 of 16 checks could reach a conclusion here; the rest do not apply to this repository or could not read it.
Fit with the Acquirer
not assessableNot rated: structurally not assessable from a repository.
Read more, or read your own
The full report on letta-ai/letta: every dimension, the questions for the room, and the audit log.
Survey a repository: free on public repositories. Private code is read on your own machine by a collector whose source you can read first.