StartupBerkeley, CA · Est. 2024 · Seed
Letta
Stateful agents with memory, from the team behind MemGPT.
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- User reportsIts MemGPT-style memory helps with long-running work: one HN user says it made long-context documentation manageable.[1]
- MetadataApache-2.0, self-hostable and popular (about 25.3k GitHub stars). The ADE lets you inspect and edit an agent's memory blocks while it runs.[1][2]
- DocsLetta Code brings its learning memory into a coding-agent harness, with headless and --yolo modes for sandboxes (per Letta staff on HN).[1][2]
- User reportsOne engineering manager said they would rather build on Letta or Mastra than trust newer personal-agent projects.[1]
Cons
- Independent testAn independent review says to avoid it for stateless apps or when the main problem is coordinating several agents, because it focuses on memory for a single agent.[1]
- User reportsMemory extraction that runs on an LLM gets expensive at scale; a competitor estimates $1k-3k per month in API calls at 100K memories a month.[1]
- User reportsA builder who tried it found that memory architectures like Letta's 'simply move the pain to retrieval'.[1]
- Best for
- Builders of long-lived, stateful single agents who want memory they can inspect and edit, and can self-host.
- Watch out for
- Budget for the extra LLM calls that memory management makes, and check retrieval quality on your own data.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Co-founder & CTO
Context engineering & memory
Co-founder & CEO
Context engineering & memory
Open roles (4)
- Research Engineer / Scientist, Memory
San Francisco Office · Full-time · Posted Sep 10, 2025
Research - Research Engineer / Scientist, Self-Improvement
San Francisco Office · Full-time · Posted Aug 15, 2025
Research - Research Engineer / Scientist, Post-Training
San Francisco Office · Full-time · Posted Feb 4, 2025
Research - Software Engineer, Agent Harness
San Francisco Office · Full-time · Posted Sep 3, 2024
Engineering
Their open-source work
Python · ≈26k stars · Apache-2.0
letta-ai/letta
Stateful agents with memory, beyond the context window.
Maintained by Letta
Activity
- Last push
- · 4w ago
- Latest release
- 0.16.8
· 6mo ago - Last 90 days
- 0 releases
0.16.8v0.16.8
· 6mo agoWhat's Changed fix: workflows update by @cpacker in https://github.com/letta-ai/letta/pull/3292 fix(security): use JSON instead of pickle for sandbox-server tool result transport by @kianjones9 in https://github.com/letta-ai/letta/pull/3343 Full Changelog:…
0.16.7v0.16.7
· 7mo agoLetta Server 0.16.7 Release Notes 173 commits since 0.16.6 Released March 31, 2026 Highlights Self-hosted users: this is a big upgrade. The default global context window is raised from 32k to 128k, the context window reset bug (LET-7991) is fixed, and compaction has been…
0.16.6v0.16.6
· 8mo agoHighlights 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…
0.16.5v0.16.5
· 9mo agoWhat's Changed chore: bump version 0.16.5 by @carenthomas in https://github.com/letta-ai/letta/pull/3202 Full Changelog: https://github.com/letta-ai/letta/compare/0.16.4...0.16.5
0.16.4v0.16.4
· 9mo agoWhat's Changed fix: update gh templates by @cpacker in https://github.com/letta-ai/letta/pull/3155 chore: release 0.16.3 by @sarahwooders in https://github.com/letta-ai/letta/pull/3158 chore: bump v0.16.4 by @carenthomas in https://github.com/letta-ai/letta/pull/3168 Full…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
On X
No posts from them in our X feed yet.
In research (4)
- LEDGER: Auditable Agent Memory Under ChangeVerdict: Useful
Nov 16, 2026 · Company behind MemGPT/Letta, a competing agent memory approach cited in related work.
Nov 16, 2026 · Commercial platform built on MemGPT-style persistent memory, the pattern the paper stress-tests.
- Learning to Remember: Advances in Memory Mechanisms for Large Language ModelsVerdict: Incremental
Oct 26, 2026 · Letta (MemGPT) is a reviewed example of OS-style hierarchical agent memory.
- Remembering Through Change: Provenance-Preserving Hypergraph Memory for Multimodal AgentsVerdict: Incremental
Oct 21, 2026 · MemGPT, now Letta, is cited as foundational agent memory.
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
San Francisco, CA · Est. 2023
Conversational AI agents for customer experience.
Sierra, co-founded by Bret Taylor and Clay Bavor, builds production conversational agents that resolve real customer issues with guardrails, evaluation and human escalation — a template for deploying vertical agents at the enterprise edge.
~$10B valuation (Oct 2025)
Coral Gables, FL · Est. 2023
Multi-agent orchestration, from open-source framework to enterprise platform.
CrewAI popularized role-based multi-agent teams ('crews') with a simple mental model and ships an enterprise control plane for deploying, monitoring and governing them.
$18M Series A led by Craft Ventures (2024)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintains · 3
- Agent FileProject
- LettaProject
- Letta CodeProject
Similar entries · 1
- LettaProject
