Letta
Letta is an open-source platform for building stateful agents - AI that keeps persistent memory and improves over time, rather than starting fresh each session. It grew out of the MemGPT research project at UC Berkeley and uses an operating-system-inspired memory model: a small always-in-context core, an external archival store the agent searches, and recall of past conversations. Letta Code, its agent harness, has posted strong results on agent benchmarks and shifted the company's focus toward agents that rewrite their own memory and skills over long horizons. There's a free tier with a few managed agents and bring-your-own-key local use, a twenty-dollar-a-month Pro plan, and enterprise options. It's a young, fast-moving project backed by a notable roster of AI researchers and investors, so the memory and stateful-agent ideas are promising but still maturing, and it's aimed at developers.
Work at Letta? Manage this listing
Our take
Letta is an open-source platform for stateful agents - AI with persistent, tiered memory that learns over time - built by the team behind MemGPT. Its Letta Code harness scores well on agent benchmarks, with a free tier and $20 Pro plan. A promising take on agent memory, though it's young, developer-facing, and still evolving fast.
Best for
Developers building long-running agents that need persistent memory and the ability to learn across sessions, not just per-chat context.
Pros
- Stateful agents with tiered, persistent memory
- Open-source, rooted in the MemGPT research
- Letta Code scores well on agent benchmarks
- Free tier plus an affordable $20 Pro plan
Cons
- Young project; APIs and approach still evolving
- Developer-facing, with a learning curve
- Memory benefits depend on careful agent design
How it compares
Where LangChain and LlamaIndex frame agents around orchestration and data, Letta centers on memory and statefulness - the agent's ability to remember and adapt - as the core problem.
Full review
Letta is an open-source platform for building stateful agents - AI that keeps persistent memory and improves over time, rather than starting fresh each session. It grew out of the MemGPT research project at UC Berkeley and uses an operating-system-inspired memory model: a small always-in-context core, an external archival store the agent searches, and recall of past conversations. Letta Code, its agent harness, has posted strong results on agent benchmarks and shifted the company's focus toward agents that rewrite their own memory and skills over long horizons. There's a free tier with a few managed agents and bring-your-own-key local use, a twenty-dollar-a-month Pro plan, and enterprise options. It's a young, fast-moving project backed by a notable roster of AI researchers and investors, so the memory and stateful-agent ideas are promising but still maturing, and it's aimed at developers.
Where LangChain and LlamaIndex frame agents around orchestration and data, Letta centers on memory and statefulness - the agent's ability to remember and adapt - as the core problem.
Cloudkart Trust Graph
3.6/5- Actual Utility4/5
Source: Initial LLM-authored rubric (backfill)
- Ease of Use3/5
Source: Initial LLM-authored rubric (backfill)
- Pricing Fairness4/5
Source: Initial LLM-authored rubric (backfill)
- Reliability3/5
Source: Initial LLM-authored rubric (backfill)
- Differentiation4/5
Source: Initial LLM-authored rubric (backfill)
Scored as of . Each score is versioned and auditable; vendors cannot buy it.
How this score is set
- Editorial rubric
- Primary signal — five dimensions, 3.6/5 average.
- Community reviews
- None yet.
- Pricing verified
- Not yet verified
- Independence
- Score set by our editorial team before any affiliate relationship is considered. No vendor can buy it.
Frequently asked questions
- Is Letta free, and how much does it cost?
- Letta is open source and free to self-host.
- Who is Letta best for?
- Developers building long-running agents that need persistent memory and the ability to learn across sessions, not just per-chat context.
- How is Letta rated on Cloudkart.ai?
- Letta scores 3.6 out of 5 on the Cloudkart.ai rubric, which weighs actual utility, ease of use, pricing fairness, reliability and differentiation. Scores are set editorially and can never be bought.
Community reviews
No community reviews yet. Be the first to share how Letta works for you.
Relevant tools
More tools in AI Coding Assistants.
Composio
Composio provides the execution infrastructure that connects AI agents to real software. It sits at the tooling and connectivity layer of the agent stack, giving developers one framework - SDKs, a CLI and 850+ pre-built connectors - to let agents act across apps such as GitHub, Slack and Salesforce. It handles the hard parts: complex authentication and OAuth, plus remote sandboxed environments for safe execution, exposed over the Model Context Protocol so agents can reason and then reliably take action. The platform is built for production, with SOC 2 and ISO 27001:2022 certifications and deployment across public cloud, VPC and on-premises. Composio operates from San Francisco and Bangalore and raised a $25M Series A led by Lightspeed, with angels including Vercel's Guillermo Rauch and HubSpot's Dharmesh Shah.
LiteLLM
LiteLLM, from BerriAI, is an open-source AI gateway that gives you a single OpenAI-compatible interface to 140+ providers and 2,500+ models, including OpenAI, Anthropic, Gemini, Bedrock, Azure, Mistral, Ollama and vLLM. You can use it as a lightweight Python SDK for direct calls, or deploy the proxy server as a centralized gateway for a team, with virtual keys, budgets, load balancing, rate limiting, request logging and LLM guardrails. It has become a default building block in the AI stack, with 45,000+ GitHub stars, 240M+ Docker pulls and over a billion requests served, and is used by companies including Netflix, Adobe and Stripe. The core is free; an enterprise tier adds JWT auth, SSO/SAML, audit logs, SLAs and dedicated support.
Claude Code
Terminal-based agentic coding tool from Anthropic for autonomous multi-step coding tasks.
Kiro
AWS agentic IDE built around spec-driven development: it writes a spec, then builds matching code, tests and docs across IDE, CLI and web.
Compare Letta head-to-head: vs Composio · vs LiteLLM · vs Claude Code · vs Kiro