Backboard
https://github.com/Backboard-io
Agent memory product evaluated against LoCoMo.
At a glance
- Type
- Memory + LoCoMo evaluation harness
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- 2025-11
- Latest release
- no releases
- License
- Unlicensed
- GitHub
- 15★ Python
- Pricing
- Usage-based tiered pricing; free production-ready tier with promo; paid tiers for scale
- Funding
- $3M pre-seed Jan 2026; co-led Mistral Venture Partners + N49P; Garage Capital + DevCap participated
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- inspectable
- conflict
- none
When to use
Optimised for: LoCoMo benchmark performance (long-conversation accuracy)
Anti-fit: searched not found
Pros & cons
Pros
Lightweight managed memory layer with simple SDK; quick to integrate into greenfield agents.
Cons
Newer entrant; thin track record; small team.
Claims & capabilities
Ships its own LoCoMo benchmark fork ( Backboard-Locomo-Benchmark ) for transparent evaluation.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Cloud-hosted (managed SaaS; multi-model API)
- 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.
Related systems
References (3)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/Gemini/Ollama keys)
- Google Gemini 3 family depends on at runtime — adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/Gemini/Ollama keys)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/Gemini/Ollama keys)