- fix: workflows update
- fix(security): use JSON instead of pickle for sandbox->server tool result transport
Letta
A platform for stateful agents with long-term memory that persists across sessions. Formerly known as MemGPT.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What Letta does
Letta is a stateful agent platform from Letta, first released in October 2023. You use it through a Python library and REST API. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic, Google, Azure, Mistral and DeepSeek and others. It is used from TypeScript. Paid plans start at $20 a month; there is a free tier.
Key facts
| Maker | Letta |
|---|---|
| Type | Stateful agent platform |
| First released | October 2023 |
| License | Apache-2.0 |
| Interfaces | Python library, REST API |
Pricing
Letta offers a free tier with 3 stateful agents (BYOK models), Pro plan at $20/month for individuals with up to 20 agents, Teams Pro at $20/seat/month for organizations, API Plan at $20/month base plus $0.10/active agent/month and usage-based LLM costs for developers, and custom Enterprise pricing. The open-source server remains free to self-host.
Source: official pricing page, checked Oct 21, 2026. Prices change often; confirm before you buy.
Letta pricing history since 2024 · Compare prices of all agents
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itPython library, REST API
- Supports MCP?Yes
- Model providersopenai, anthropic, google, azure, mistral, deepseek, xai, any OpenAI-compatible, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in Letta: May 2026
May brought security improvements and bug fixes to Letta. The month focused on stability and safer data handling between components.
- Security fix: tool results now use JSON instead of pickle for safer data transport between sandbox and server
1 release this month · summarised from the official release notes · all months
Get started with Letta
| PyPI | pip install letta |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for Letta: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Letta or for agent frameworks in general. Savings and results depend on your workload.
Letta alternatives
Best Letta alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Tools used with Letta
What 29 public GitHub projects that depend on Letta use with it, from their dependency files.
- python-dotenv62.1%
- Pydantic37.9%
- Requests34.5%
- OpenAI Python Library31.0%
- pytest31.0%
- Uvicorn24.1%
- Mem0 (Python)20.7%
- FastAPI20.7%
- Chroma (Python)20.7%
- LangChain20.7%
Used far more often here than in AI-built projects overall: what sets Letta projects apart.
- Letta Client13.8% · 862.6×
- E2B Code Interpreter (Python)3.4% · 215.7×
- Mem0 (Python)20.7% · 129.4×
- CrewAI6.9% · 107.8×
- vLLM3.4% · 107.8×
- pypdfium26.9% · 53.9×
- Google Agent Development Kit6.9% · 53.9×
- sqlite-vec (Python)3.4% · 35.9×
Ratings from people who use Letta
No ratings yet. Used Letta? Rate it and say what it is good and bad at.
What changed: recent Letta releases
- Block limits are no longer enforced -- block limit validation has been deprecated and removed from the git memory sync path. Blocks can now grow freely.
- Global context window default raised from 32k to 128k -- self-hosted servers no longer default to 32k for unknown models
- Context window preserved on conversation model override (LET-7991, #9986) -- the bug where non-default conversations fell back to 32k is fixed
- Compaction overflow fixes -- addresses the double-compaction and runaway compaction loops
- Compaction model resets on agent model change -- switching your agent's model no longer leaves the old summarizer model behind
- Summarizer prompt improved -- now remembers plan files, GitHub PRs, and other structured content during summarization
Earlier releases
- Expanded Conversations API support for default conversation / agent-direct mode.
- New conversations now initialize with a compiled system message at creation time.
- Fixed model_settings.max_output_tokens default behavior so it does not silently override existing max_tokens unless explicitly set.
- Added support for conversation_id="default" + agent_id across conversation endpoints (send/list/cancel/compact/stream retrieve).
- Kept backwards compatibility for conversation_id=agent-* (deprecated path).
- Added lock-key handling in agent-direct flows to avoid concurrent execution conflicts.
- chore: bump version 0.16.5
- fix: update gh templates
- chore: release 0.16.3
- chore: bump v0.16.4
- docs: update README.md
- Update contributing.md with corrected local setup steps
- chore: bump version 0.16.2
- @neversettle17-101 made their first contribution in
Letta prices over time
Letta popularity and usage data
Letta was downloaded 2,909 times from PyPI in the week ending Nov 17, 2026, up 9.8% on the week before and down 70.0% over the last 30 days compared with the 30 before. Its download count moved to a different level overnight on Sep 16, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 25.5K stars, 334 of them added in the last 30 days. The latest stable release is 0.16.8, published May 14, 2026. It was mentioned in 3 Hacker News posts and comments over the last 30 days.
Download the raw daily series: letta.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Letta FAQ
How much does Letta cost?
Letta offers a free tier with 3 stateful agents (BYOK models), Pro plan at $20/month for individuals with up to 20 agents, Teams Pro at $20/seat/month for organizations, API Plan at $20/month base plus $0.10/active agent/month and usage-based LLM costs for developers, and custom Enterprise pricing. The open-source server remains free to self-host.
Is Letta open source?
Yes. Letta is open source, released under the Apache-2.0 license.
How popular is Letta?
Letta was downloaded 2,909 times from PyPI in the week ending Nov 17, 2026, up 9.8% on the week before and down 70.0% over the last 30 days compared with the 30 before. Its download count moved to a different level overnight on Sep 16, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 25.5K stars, 334 of them added in the last 30 days.
What is the latest version of Letta?
The latest stable release we track is 0.16.8, published on May 14, 2026.
What are the alternatives to Letta?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of Letta badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/letta/)
[](https://agentgid.com/agents/letta/)
[](https://agentgid.com/agents/letta/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: letta. GitHub: letta-ai/letta. See data sources for how each one is collected.