Skip to content
RankShark

Letta

Platform for stateful agents with long-term memory.

ToolOpen sourceby Lettasince 2023
60.1

SharkScore

#159 in Frameworks & SDKs

Why it scores 60.1

Letta has a SharkScore of 60.1/100, ranked #159 of 665 in Frameworks & SDKs (updated 2026-11-19).

Each part compares Letta with other listings in Frameworks & SDKs. Evidence covers 87% of the score's weight.

Adoption
45 · 30%
User reviews
no data · 25%
Maintenance
88 · 20%
Trust & transparency
60 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Letta

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Letta presents Letta Code as an agent whose memory, identity, and capabilities evolve; RankShark measured release 0.16.8 on 2026-05-14. [E1; MEASURED]

Letta describes itself as an AI research lab and presents Letta Code as software for an agent whose memory, identity, and capabilities evolve with experience. [E1]

Best for

  • Developers exploring agents that use memory and continual learning. [E1] · home page
  • Users who want to run their own model backends, which Letta says means their message and prompt data will not be collected by Letta. [E2] · privacy page

Not for

  • Teams that require a stated fixed retention period; the policy describes when data is generally discarded but gives no fixed duration. [E2] · privacy page

Key features

  • Letta Code. The vendor says Letta Code is an AI agent whose memory, identity, and capabilities evolve with experience. [E1] · home page
  • Git-based context management. The vendor describes Context Repositories as programmatic context management with git-based versioning. [E1] · home page
  • Memory models. The vendor describes research into memory models trained with memory-native reinforcement learning to support agent learning. [E1] · home page
  • Installation. The vendor gives an npm command for installing Letta Code globally. [E1] · home page

Pros

  • The product description and research focus explicitly cover agent memory and continual learning. [E1] · home page
  • The policy says prompts and messages are not collected when users run their own model backends. [E2] · privacy page

Cons

  • For hosted services, Letta says it collects data used to render the service and may use it to improve services or train future models. [E2] · privacy page
  • The privacy policy does not give a fixed retention duration. [E2] · privacy page
  • No public prices found on the pages we checked.
  • No free plan or free trial stated on the pages we checked.
  • No release in the last 180 days (latest: 0.16.8 on 2026-05-14).

Pricing

No public prices found on the pages we checked.

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
The vendor says it may use data collected through hosted services to improve services and train future models; it says it does not collect messages or prompts when users run their own model backends. [E2] · privacy page
Data retention
The policy says it retains model inputs and outputs only when users use hosted services and generally discards information when it is no longer needed, without specifying a fixed period. [E2] · privacy page
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Not stated (checked 18 Nov 2026)
API
Not stated (checked 18 Nov 2026)
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
Not stated (checked 18 Nov 2026)
Security claims
The vendor says it monitors its services for potential vulnerabilities and attacks. [E2] · privacy pageThe vendor says it takes reasonable measures to protect information against unauthorized access, use, alteration, or destruction. [E2] · privacy page

What we measured

GitHub stars · now
25,472
Latest release · now
0.16.8 on 2026-05-14
Package downloads · 30 days
417,686
Tranco traffic rank · list of the day
#145,627
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Letta

See all
  • 81.7

    Open protocol and SDKs that connect AI apps to tools and data.

    ToolOpen source
  • 77.7

    TypeScript toolkit for building AI apps and agents.

    ToolOpen source
  • 77.7

    Build agents and LLM apps in Python and TypeScript.

    ToolOpen source
  • 76.9

    Tracing, evaluation and monitoring for LLM apps.

    ToolFreemium · from $39/mo