Hyperspell
https://www.ycombinator.com/companies/hyperspell
YC F25 'company brain': connects 50+ sources (Slack, Gmail, Notion, Drive...) into a permission-aware context graph served to agents via API/SDK, returning structured results or LLM-ready summaries; learns from queries over time.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 36 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Workplace agent memory connectors vendor fix
- Tier
- T2
- Section
- Dedicated memory layers
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- not public — book a demo vendor fix
- Funding
- $2M Seed · 2025-09 vendor fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- python, rest, typescript registry fix
- Protocols
- mcp-server vendor fix
- Compliance
- gdpr, hipaa, soc2-type2 vendor fix
Memory taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- document
- governance
- opaque
- conflict
- none
When to use
Optimised for: workplace connectors + cross-source recall
Anti-fit: not for non-workplace consumer use cases
Pros & cons
Pros
Spell-as-memory framing — invocations are first-class, not just facts; useful for skill-heavy agents.
Cons
Niche framing; smaller community; integration story still maturing.
Claims & capabilities
YC F25. Founders previously scaled API products to $30M ARR.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Cloud API + SDK (no self-hosted option found)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- unclear — official hyperspell-mcp repo is archived; current integration via SDKs/CLI into Claude Code, Codex, Cursor
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to Hyperspell → live options ranked by shared design, licence, hosting and MCP support
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 (35 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 it is Workplace agent memory connectors vendor
- What it does & what's distinct YC F25 'company brain': connects 50+ sources (Slack, Gmail, Notion, Drive...) into a per… vendor
- Claims / benefits YC F25. Founders previously scaled API products to $30M ARR. vendor
- Modalities text vendor
- Created 2024 vendor
- Funding $2M Seed · 2025-09 vendor
- Customers / scale 1-10 ppl Developer teams, agent memory for Slack Gmail Notion vendor
- Pricing not public — book a demo vendor
- Deployment Cloud API + SDK (no self-hosted option found) vendor
- HQ US vendor
- Founders / pedigree YC F25; founders previously scaled API products to $30M ARR vendor
- Memory volume / scale no scale claim vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- MCP support unclear — official hyperspell-mcp repo is archived; current integration via SDKs/CLI int… repo
- Integration count 0 vendor
- Orchestration single-agent vendor
- Programmatic control SDK + connector-config (declarative) vendor
- Validated verticals knowledge management, internal productivity (Slack/Gmail/Notion/Drive) vendor
- Time to running <10min (hosted) - SaaS connectors vendor
- Anti-fit not for non-workplace consumer use cases vendor
- Optimised for workplace connectors + cross-source recall vendor
- Adjacent infrastructure BYO LLM; managed connectors + vectors vendor
- Pros Spell-as-memory framing — invocations are first-class, not just facts; useful for skill-… vendor
- Cons Niche framing; smaller community; integration story still maturing. vendor
- Project & sources YC company page vendor
- adoption-accelerator yc-f25 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications gdpr,hipaa,soc2-type2 vendor
- sdk-languages python,rest,typescript registry
- protocol-support mcp-server vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)