Anda Hippocampus (now Anda Brain)

https://github.com/ldclabs/anda-brain

Renamed Anda Brain (repo now ldclabs/anda-brain). Native graph-based memory for autonomous AI agents. Bio-inspired sleep-based memory consolidation. The hosted service brain.anda.ai has been discontinued; Anda Brain is now self-hosted only (Rust service or Cloudflare Worker).

Shut down. discontinued; now Anda Brain Source · Alternatives and migration notes →

Shut down · Verified 2026-10-29 · fresh as of 2026-10-29 · 48 cited facts, 0 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T2
Created
2026-03 repo fix
Latest release
v0.13.5 (2026-10-17) repo fix
License
Apache-2.0 repo fix
Funding
searched not found fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source repo fix
Deployment locus
local repo fix
Platform vs product
platform repo fix

Memory taxonomy

storage
graph
retrieval
graph-traversal
persistence
long-term
update
consolidation
unit
episode
governance
opaque
conflict
none

When to use

Optimised for: bio-inspired sleep consolidation (research positioning)

Anti-fit: no anti-fit explicitly stated

Pros & cons

Pros

Hippocampus-inspired neural memory model — explicit episodic encoding and consolidation.

Cons

Research-oriented; production deployment limited.

Claims & capabilities

Apache-2.0 + MIT; bio-inspired sleep-based memory consolidation; native graph for autonomous AI agents; v0.4.17 released 2026-05-05; from LDC Labs (creators of ICPanda DAO on ICP blockchain); Rust implementation

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Self-hosted on-premises (full data privacy; no cloud service)
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
yes — built-in MCP server (Streamable HTTP at /mcp/{space_id} and stdio), memory/recall tools
A2A
not supported
OpenTelemetry
not documented publicly

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 (47 cited facts, 0 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 “Anda Hippocampus” → “Anda Hippocampus (now Anda Brain)”
    • Homepage “https://github.com/ldclabs/anda-hippocampus” → “https://github.com/ldclabs/anda-brain”
    #223
  2. 2026-10-22
    • Latest release “v0.4.17 2026-05-05” → “v0.13.5 (2026-10-17)” source
    • MCP support first recorded as “yes — built-in MCP server (Streamable HTTP at /mcp/{space_id} and stdio), memory/recall tools” source
    #195