Trace
https://www.ycombinator.com/companies/trace-so
YC S25 + $3M seed (Feb 2026). Workflow orchestration mapping corporate environments as a structured context graph so agents always have institutional knowledge for tasks. CTO frames differentiator as "context engineering."
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 32 cited facts, 10 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Context-graph / KG memory 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 — beta with waitlist / contact vendor fix
- Funding
- $3M total Seed · 2026-02 third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
Memory taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- inspectable
- conflict
- none
When to use
Optimised for: context-graph KG memory for agents
Anti-fit: searched not found
Pros & cons
Pros
Trace-based memory model — every reasoning step is recorded and recallable for debugging.
Cons
Trace volume can balloon; not a pure storage layer — memory is incidental to debugging focus.
Claims & capabilities
YC + Zeno + Transpose + Goodwater + Formosa + WeFunder ($3M Feb 2026).
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Cloud (SaaS integrating Slack/Jira/Notion; no self-hosted option found)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- not documented publicly
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to Trace → 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 (31 cited facts, 10 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Context-graph / KG memory vendor
- What it does & what's distinct YC S25 + $3M seed (Feb 2026). Workflow orchestration mapping corporate environments as a… vendor
- Claims / benefits YC + Zeno + Transpose + Goodwater + Formosa + WeFunder ($3M Feb 2026). vendor
- Modalities text vendor
- Created 2026-02 third-party
- Mindshare 1 press ~10 (seed-stage jobs third-party
- Funding $3M total Seed · 2026-02 third-party
- Customers / scale 30+ companies at public launch (no names disclosed) third-party
- Pricing not public — beta with waitlist / contact vendor
- Deployment Cloud (SaaS integrating Slack/Jira/Notion; no self-hosted option found) third-party
- HQ UK (London) / also described as SF-area; Tim Cherkasov + Artur Romanov based in London third-party
- Founders / pedigree YC W26; co-founders Tim and Artur (no further public background found) vendor
- Memory volume / scale no scale claim third-party
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- Integration count 0 vendor
- Orchestration agnostic vendor
- Validated verticals agent developers (horizontal) third-party
- Time to running <10min (hosted SaaS) third-party
- Optimised for context-graph KG memory for agents third-party
- Adjacent infrastructure BYO LLM (browser-agent runtime; user supplies model keys) vendor
- Pros Trace-based memory model — every reasoning step is recorded and recallable for debugging. vendor
- Cons Trace volume can balloon; not a pure storage layer — memory is incidental to debugging f… vendor
- Project & sources YC page TC coverage vendor
- adoption-accelerator yc-s25 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- maturity beta vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)