NeoCognition
Builds agents that learn from experience by constructing a "world model" of the micro-environment they operate in. Specialise over time through Agentic RL loop rather than relying on static prompt context. Targets the ~50% task-completion failure rate in current agents.
At a glance
- Type
- World-model / experiential self-learning memory
- Tier
- T1
- Section
- Dedicated memory layers
- Created
- 2026-04
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- searched not found
- Funding
- $40M total Seed · 2026-04
Taxonomy
- storage
- hybrid
- retrieval
- agentic
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- opaque
- conflict
- none
When to use
Optimised for: world-model / experiential learning
Anti-fit: searched not found
Pros & cons
Pros
Cognitive-architecture-inspired model with explicit episodic/semantic separation reflects long-standing memory science.
Cons
More academic than commercial; limited production deployment evidence.
Claims & capabilities
$40M seed (April 2026, Cambium Capital + Walden Catalyst). Angel investors include Intel CEO Lip-Bu Tan, Databricks's Ion Stoica.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- searched not found
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- not documented publicly
- A2A
- not documented publicly
- 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.
- Memvid T2
Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).
- Supermemory T1
Memory engine with API, app, browser extension, and MCP server. Extracts facts, tracks updates, resolves contradictions, auto-forgets expired info. Plugins for Claude Code, OpenCode, OpenClaw, Hermes.