{"id":"letta-memgpt--letta-com","name":"Letta / MemGPT","url":"https://www.letta.com/","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/letta-memgpt--letta-com","family":"memory","section":"Dedicated memory layers","sections":["Dedicated memory layers"],"tier":1,"last_verified_at":"2026-10-29","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"kv","primary":true,"reason":null},{"value":"vector","primary":false,"reason":null}],"retrieval":[{"value":"similarity","primary":true,"reason":null},{"value":"injection","primary":false,"reason":null},{"value":"agentic","primary":false,"reason":null}],"persistence":[{"value":"long-term","primary":true,"reason":null}],"update":[{"value":"agent-controlled","primary":true,"reason":null}],"unit":[{"value":"episode","primary":true,"reason":null},{"value":"summary","primary":false,"reason":null},{"value":"fact","primary":false,"reason":null}],"governance":[{"value":"inspectable","primary":true,"reason":null}],"conflict":[{"value":"llm-arbitrate","primary":true,"reason":"LLM-arbitrate: agent autonomously decides when to update core memory blocks via tool calls (memory_replace / memory_insert)"}]},"cells":{"type":{"value":"Tiered: core / recall / archival","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.","citation":"https://github.com/letta-ai/letta-code","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"$10M seed at $70M (Sep 2024). Reports ~83.2% on LongMemEval; ~74.0% on LoCoMo with gpt-4o-mini using files-as-memory.","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"text","citation":"https://docs.letta.com/concepts/memgpt/","status":"real-data","tier":"T2","source_class":"vendor"},"created":{"value":"2023-10","citation":"https://www.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"latest-release":{"value":"Letta Code v0.34.30 (npm @letta-ai/letta-code, 2026-10-29); PyPI letta v0.34.12 (2026-10-12); last letta-ai/letta server tag v0.16.8 (May 2026)","citation":"https://www.npmjs.com/package/@letta-ai/letta-code","status":"real-data","tier":"T2","last_verified_at":"2026-10-29","source_class":"registry"},"license":{"value":"Apache-2.0","citation":"https://github.com/letta-ai/letta/blob/main/LICENSE","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"letta-ai/letta-code — ~3.7k stars, Apache-2.0 (current source: agent harness, terminal UI, App Server); letta-ai/letta (~25.3k stars, not archived) is now a README pointing to letta-code, with the retired Letta V1 API server on its archive branch","citation":"https://github.com/letta-ai/letta-code","status":"real-data","tier":"T1","last_verified_at":"2026-10-29","source_class":"repo"},"mindshare":{"value":"searched not found","citation":"https://github.com/letta-ai/letta","status":"depth-floor-reached","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"citations":{"value":"not applicable — not academic","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"funding":{"value":"$10M total $70M val Seed · 2024-09","citation":"https://techcrunch.com/2024/09/23/letta-one-of-uc-berkeleys-most-anticipated-ai-startups-has-just-come-out-of-stealth/","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"third-party"},"customers":{"value":"$1M ARR 11-50 ppl No named enterprise customers disclosed","citation":"https://getlatka.com/companies/letta.com","status":"real-data","tier":"T2","source_class":"third-party"},"pricing":{"value":"Free $0 (3 agents); Pro $20/mo; Developer pay-as-you-go ($0.10/active agent/mo); Teams; Enterprise custom","citation":"https://docs.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"compliance":{"value":"not documented publicly","citation":"https://www.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"data-handling":{"value":"searched not found","citation":"https://letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"deployment":{"value":"Both","citation":"https://docs.letta.com/concepts/memgpt/","status":"real-data","tier":"T2","source_class":"vendor"},"hq":{"value":"US","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"founders":{"value":"UC Berkeley Sky Computing Lab spin-off; co-founders Charles Packer and Sarah Wooders (both Berkeley PhD students; created MemGPT); $10M seed led by Felicis at $70M post-money","citation":"https://techcrunch.com/2024/09/23/letta-one-of-uc-berkeleys-most-anticipated-ai-startups-has-just-come-out-of-stealth/","status":"real-data","tier":"T2","source_class":"third-party"},"volume":{"value":"no scale claim","citation":"https://www.letta.com/blog/benchmarking-ai-agent-memory","status":"real-data","tier":"T2","source_class":"vendor"},"perf":{"value":"74.0% LoCoMo 83.2% LMES","citation":"https://www.letta.com/blog/benchmarking-ai-agent-memory","status":"real-data","tier":"T2","source_class":"vendor"},"repro":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"code-release":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"api-surface":{"value":"REST, SDK: Python, TS","citation":"https://docs.letta.com/api-reference/overview","status":"real-data","tier":"T2","source_class":"vendor"},"latency":{"value":"searched not found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"throughput":{"value":"searched not found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"backend-storage":{"value":"Postgres + pgvector","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"multi-tenancy":{"value":"Logical namespace per org/project/agent; self-hosted Docker option for hard tenant isolation","citation":"https://docs.letta.com/concepts/agents","status":"real-data","tier":"T2","source_class":"vendor"},"encryption":{"value":"AES-256 at rest, TLS in transit (Letta Cloud on managed cloud)","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"sso-rbac":{"value":"SSO + RBAC","citation":"https://www.letta.com/security","status":"real-data","tier":"T2","source_class":"vendor"},"embedding-model":{"value":"multiple supported","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"consistency":{"value":"strong","citation":"https://docs.letta.com/concepts/memgpt","status":"real-data","tier":"T2","source_class":"vendor"},"versioning":{"value":"snapshots","citation":"https://docs.letta.com/concepts/agent-state","status":"real-data","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"hard-delete supported","citation":"https://docs.letta.com/api-reference/agents/delete-agent","status":"real-data","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"schema with migration","citation":"https://docs.letta.com/concepts/blocks","status":"real-data","tier":"T2","source_class":"vendor"},"namespace":{"value":"per-user","citation":"https://docs.letta.com/concepts/agents","status":"real-data","tier":"T2","source_class":"vendor"},"contradiction":{"value":"LLM resolves and overwrites","citation":"https://docs.letta.com/concepts/memgpt","status":"real-data","tier":"T2","source_class":"vendor"},"forgetting":{"value":"consolidation/summarization","citation":"https://docs.letta.com/concepts/memgpt","status":"real-data","tier":"T2","source_class":"vendor"},"mcp-support":{"value":"native (first-party) — Letta serves & consumes MCP","citation":"https://docs.letta.com/guides/mcp","status":"real-data","tier":"T2","source_class":"vendor"},"a2a-support":{"value":"not documented publicly","citation":"https://www.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"otel":{"value":"not documented publicly","citation":"https://www.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"webhooks":{"value":"not documented publicly","citation":"https://www.letta.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"import-export":{"value":"JSON agent file (.af) export/import","citation":"https://docs.letta.com/guides/server/agent-file","status":"real-data","tier":"T2","source_class":"vendor"},"integration-count":{"value":"1","citation":"https://github.com/letta-ai/letta (network analysis: 0 inbound from catalog rows; comparator only)","status":"real-data","tier":"T1","source_class":"repo"},"orchestration":{"value":"single-agent (per agent: core, archival, recall memory blocks)","citation":"https://docs.letta.com/concepts/agent","status":"real-data","tier":"T2","source_class":"vendor"},"programmatic-control":{"value":"full CRUD + SDK (Python/TS REST)","citation":"https://docs.letta.com/api-reference","status":"real-data","tier":"T2","source_class":"vendor"},"vendor-benchmarks":{"value":"LMES 83.2 (vendor); LoCoMo 74.0 with gpt-4o-mini (vendor)","citation":"https://www.letta.com/blog/benchmarking-ai-agent-memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"pricing-specifics":{"value":"per-message + per-agent tier flat-rate: Letta Cloud Free; Pro $20/mo; Enterprise custom; OSS self-hosted free","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"agent-abstraction":{"value":"N/A — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"N/A — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"N/A — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"N/A — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"N/A — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"consumer / individual, research, agent developers (horizontal)","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"time-to-running":{"value":"<1hr (Docker compose, OSS) or hosted Letta Cloud","citation":"https://docs.letta.com/quickstart","status":"real-data","tier":"T2","source_class":"vendor"},"anti-fit":{"value":"no anti-fit explicitly stated","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"optimised-for":{"value":"LLM-as-OS paradigm; agent autonomy in managing its own memory","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"adjacent-infrastructure":{"value":"BYO LLM (OpenAI/Anthropic/local); bundled storage (Postgres/SQLite)","citation":"https://docs.letta.com/install","status":"real-data","tier":"T2","source_class":"vendor"},"pros":{"value":"Most architecturally principled — explicit OS-style tiering makes capacity behavior predictable; UC Berkeley origin + active v1 maturity.","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"cons":{"value":"Tier configuration adds operational complexity vs flat vector memory; latency is sensitive to paging decisions on long histories.","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"links":{"value":"GitHub letta-ai/letta Letta docs v1 agent blog agent memory blog benchmarking","citation":"https://www.letta.com/","status":"real-data","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-opentelemetry":{"value":"yes","citation":"https://docs.letta.com/concepts/tracing","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-datadog":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-helicone":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-weave":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-langfuse":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-arize":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.letta.com/","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-custom":{"value":"First-party OpenTelemetry tracing in Letta Server","citation":"https://docs.letta.com/concepts/tracing","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-token-budget":{"value":"yes","citation":"https://docs.letta.com/concepts/agent-development-environment","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-prompt-caching":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-semantic-caching":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-batching":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-model-routing":{"value":"yes","citation":"https://docs.letta.com/llm-models","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-streaming-only":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-observability-cost-attribution":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-langsmith-evals":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-braintrust":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-weights-and-biases-agent":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-helicone-evals":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-custom-test-harness":{"value":"yes","citation":"https://docs.letta.com/guides/agents/testing","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-human-loop":{"value":"yes","citation":"https://docs.letta.com/concepts/agent-development-environment","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-production-traffic-replay":{"value":"no","citation":"https://docs.letta.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"commit-trajectory":{"value":"[{\"ym\":\"2025-11\",\"cum\":6578},{\"ym\":\"2025-12\",\"cum\":6733},{\"ym\":\"2026-01\",\"cum\":7043},{\"ym\":\"2026-02\",\"cum\":7244},{\"ym\":\"2026-03\",\"cum\":7460},{\"ym\":\"2026-04\",\"cum\":7463},{\"ym\":\"2026-05\",\"cum\":7464}]","citation":"https://github.com/letta-ai/letta","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"[{\"ym\":\"2025-11\",\"monthly\":9282,\"cum\":9282},{\"ym\":\"2025-12\",\"monthly\":31216,\"cum\":40498},{\"ym\":\"2026-01\",\"monthly\":40272,\"cum\":80770},{\"ym\":\"2026-02\",\"monthly\":89510,\"cum\":170280},{\"ym\":\"2026-03\",\"monthly\":97729,\"cum\":268009},{\"ym\":\"2026-04\",\"monthly\":90747,\"cum\":358756}]","citation":"https://pypi.org/project/letta/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"registry"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-tier":{"value":"free","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"free-tier","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-last-verified":{"value":"2026-06-29","citation":"https://www.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"68","citation":null,"status":"estimate","tier":"T3"},"capability-band":{"value":"competent","citation":null,"status":"estimate","tier":"T3"},"capability-benchmark-sources":{"value":"Letta ~83.2% on LongMemEval (2025), ~74.0% on LoCoMo with gpt-4o-mini (2025)","citation":null,"status":"estimate","tier":"T3"},"capability-last-verified":{"value":"2026-06-29","citation":null,"status":"estimate","tier":"T3"},"use-case-tags":{"value":"long-running-session, memory-augmented-chat, multi-agent-coordination","citation":null,"status":"estimate","tier":"T3"},"use-case-anti-tags":{"value":"latency-sensitive, scoped-agentic","citation":null,"status":"estimate","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"hybrid","citation":"https://github.com/letta-ai/letta","status":"real-data","tier":"T1","source_class":"repo"},"licensing-bucket":{"value":"open-core","citation":"https://docs.letta.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"positioning-platform-vs-product":{"value":"both","citation":"https://github.com/letta-ai/letta","status":"real-data","tier":"T1","source_class":"repo"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"{\"activity\":20.5,\"as_of\":\"2026-09\",\"openrank_12mo\":5.04,\"openrank_current\":0.7,\"participants\":11}","citation":"https://oss.open-digger.cn/github/letta-ai/letta/openrank.json","status":"real-data","tier":"T2","last_verified_at":"2026-10-28","source_class":"third-party"},"freshness-date":{"value":"2026-10-29","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/letta-memgpt--letta-com","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"python,rest,typescript","citation":"https://docs.letta.com/llms.txt","status":"real-data","tier":"T2","source_class":"vendor"},"protocol-support":{"value":"mcp-client,mcp-server","citation":"https://docs.letta.com/platform/hosted-mcp/index.md","status":"real-data","tier":"T2","source_class":"vendor"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":74,"third_party_cells":4},"edges":{"outgoing":[{"source":"letta-memgpt--letta-com","target":"anthropic-claude-foundation-models--anthropic-com","type":"integrates-with","evidence":"Letta models docs list Anthropic API in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"anthropic-claude-foundation-models--anthropic-com","type":"runtime-dependency","evidence":"adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/local); bundled storage (Postgres/SQLite)","citation":"https://docs.letta.com/install"},{"source":"letta-memgpt--letta-com","target":"deepseek-r1-v3-family--deepseek-com","type":"integrates-with","evidence":"Letta models docs list DeepSeek in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"fireworks-ai--fireworks-ai","type":"integrates-with","evidence":"Letta models docs list Fireworks in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"google-gemini-3-family--blog-google","type":"integrates-with","evidence":"Letta models docs list Google Gemini in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"mistral-large-2-mixtral-family--mistral-ai","type":"integrates-with","evidence":"Letta models docs list Mistral in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"model-context-protocol-mcp-spec--modelcontextprotocol-io","type":"integrates-with","evidence":"Letta Agent SDK docs cover connecting sessions to stdio, HTTP and SSE MCP servers.","citation":"https://docs.letta.com/agent-sdk/mcp/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"openai-gpt-family-gpt-5-gpt-4o-o3-o4--openai-com","type":"integrates-with","evidence":"Letta models docs list OpenAI API in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"openai-gpt-family-gpt-5-gpt-4o-o3-o4--openai-com","type":"runtime-dependency","evidence":"adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/local); bundled storage (Postgres/SQLite)","citation":"https://docs.letta.com/install"},{"source":"letta-memgpt--letta-com","target":"openrouter--openrouter-ai","type":"integrates-with","evidence":"Letta models docs list OpenRouter in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"pgvector--gh-pgvector-pgvector","type":"runtime-dependency","evidence":"backend-storage cell: Postgres + pgvector","citation":"https://docs.letta.com/"},{"source":"letta-memgpt--letta-com","target":"together-ai--together-ai","type":"integrates-with","evidence":"Letta models docs list Together AI in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"},{"source":"letta-memgpt--letta-com","target":"xai-grok-4--x-ai","type":"integrates-with","evidence":"Letta models docs list xAI in the supported model provider table.","citation":"https://docs.letta.com/configuration/models/","verified_at":"2026-10-29"}],"incoming":[{"source":"e2b--e2b-dev","target":"letta-memgpt--letta-com","type":"integrates-with","evidence":"E2B docs have a Letta / MemGPT integration guide.","citation":"https://docs.e2b.dev/agents/letta","verified_at":"2026-10-29"},{"source":"livekit-agents--docs-livekit-io","target":"letta-memgpt--letta-com","type":"integrates-with","evidence":"LiveKit Agents docs have a Letta / MemGPT model plugin page.","citation":"https://docs.livekit.io/agents/models/llm/letta/","verified_at":"2026-10-29"},{"source":"milvus--milvus-io","target":"letta-memgpt--letta-com","type":"integrates-with","evidence":"Milvus's integrations overview lists a Milvus + Letta / MemGPT integration tutorial.","citation":"https://milvus.io/docs/integrations_overview.md","verified_at":"2026-10-29"},{"source":"pydantic-logfire--pydantic-dev","target":"letta-memgpt--letta-com","type":"integrates-with","evidence":"Pydantic Logfire integrations docs have a Letta page.","citation":"https://pydantic.dev/docs/logfire/integrations/llms/letta/","verified_at":"2026-10-29"},{"source":"vercel-ai-sdk--sdk-vercel-ai","target":"letta-memgpt--letta-com","type":"integrates-with","evidence":"AI SDK docs have a Letta community provider page.","citation":"https://ai-sdk.dev/providers/community-providers/letta","verified_at":"2026-10-29"}]},"history":[{"date":"2026-10-29","commit":"6895ae8e38","pr":307,"kind":"update","changes":[{"field":"latest-release","label":"Latest release","from":"Letta Code (PyPI letta) v0.34.12 (2026-10-12); last letta-ai/letta server tag v0.16.8 (May 2026)","to":"Letta Code v0.34.30 (npm @letta-ai/letta-code, 2026-10-29); PyPI letta v0.34.12 (2026-10-12); last letta-ai/letta server tag v0.16.8 (May 2026)","source":"https://www.npmjs.com/package/@letta-ai/letta-code"}]},{"date":"2026-10-22","commit":"89dcc719ed","pr":195,"kind":"update","changes":[{"field":"latest-release","label":"Latest release","from":"0.16.7 2026-03-31","to":"Letta Code (PyPI letta) v0.34.12 (2026-10-12); last letta-ai/letta server tag v0.16.8 (May 2026)","source":"https://pypi.org/project/letta/"},{"field":"pricing","label":"Pricing","from":"Free + paid","to":"Free $0 (3 agents); Pro $20/mo; Developer pay-as-you-go ($0.10/active agent/mo); Teams; Enterprise custom","source":"https://docs.letta.com/pricing"}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}