Memori (GibsonAI) (now Memori Labs)

https://github.com/MemoriLabs/Memori

Now Memori by Memori Labs (repo moved to MemoriLabs/Memori; adds managed Memori Cloud and BYODB). SQL-native memory engine for AI agents — single library, opt-in conscious/auto modes, structured Pydantic outputs. Aims to be 'one line of code' to add memory to any LLM workflow.

Renamed. now Memori Labs Source · Alternatives and migration notes →

Renamed · Verified 2026-10-23 · fresh as of 2026-10-23 · 21 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T3
Created
2025-06 repo fix
Latest release
v3.3.6 (2026-05-28) repo fix
License
Apache-2.0 repo fix
Funding
searched not found fix
Freshness
2026-10-23 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid repo fix
Platform vs product
platform repo fix
Maturity
alpha registry fix
SDK languages
python, typescript repo fix
Protocols
mcp-server repo fix

Memory taxonomy

storage
kv
retrieval
similarity
persistence
long-term
update
extraction
unit
fact
governance
plaintext
conflict
n/a

When to use

Optimised for: searched not found

Anti-fit: searched not found

Pros & cons

Pros

searched not found

Cons

searched not found

Claims & capabilities

Multi-DB support (SQLite/Postgres/MySQL); Pydantic-validated entity extraction; LiteLLM/Anthropic/OpenAI providers.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Both — OSS SDK self-hosted; Memori Cloud managed; enterprise single-tenant/VPC/on-prem
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
yes — hosted remote MCP endpoint for Claude Code, Cursor, Codex, Warp, Antigravity (no SDK needed)
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other dedicated memory layers in the catalog, ranked by inbound references.

  • Mem0 T1

    Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

  • Zep & Graphiti T1

    Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

  • Cognee T1

    "Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

  • Hindsight (Vectorize) T1

    Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

  • Letta / MemGPT T1

    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.

  • Memori T2

    Structured, persistent memory layer for AI agents. Open source.

Sources (20 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-23
    • Name “Memori (GibsonAI)” → “Memori (GibsonAI) (now Memori Labs)”
    • Homepage “https://github.com/GibsonAI/memori” → “https://github.com/MemoriLabs/Memori”
    #223
  2. 2026-10-22
    • Latest release first recorded as “v3.3.6 (2026-05-28)” source
    • Pricing first recorded as “OSS free (Apache-2.0); Memori Cloud API key with free developer tier (rate-limited); enterprise by contact” source
    • Deployment first recorded as “Both — OSS SDK self-hosted; Memori Cloud managed; enterprise single-tenant/VPC/on-prem” source
    • MCP support first recorded as “yes — hosted remote MCP endpoint for Claude Code, Cursor, Codex, Warp, Antigravity (no SDK needed)” source
    #195