Ross ROSS = Recommend OSS · open-source software intelligence for agents

hashintel/hash

🚀 The open-source, multi-tenant platform for self-building knowledge graphs and simulation observed · 2026-08-28

github.com/hashintel/hash · homepage · TypeScript · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

99/100

  • Activity 99
  • Release rhythm 99
  • Longevity 100

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 2606
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 34

Full methodology

Adoption not part of the score

1649 stars · 122 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

HASH is an open-source, multi-tenant platform for building self-maintaining knowledge graphs and process graphs, powered by the hgres graph engine, the SemType semantic type system, and the HashQL query language. It ingests structured and unstructured data into a bitemporal, provenance-aware graph, with AI agents that grow, check, and maintain the database, plus simulation tooling (Petrinaut) and a web UI for browsing entities and types.

Use cases

  • build a self-updating knowledge graph from documents and databases
  • integrate and reconcile data from multiple sources into semantic entities
  • model business processes and run simulations on a typed graph
  • track when facts happened and when they became known (bitemporal data)
  • let AI agents maintain and structure a shared source of truth
  • browse and edit typed entities and schemas visually
  • build decision-support tools on top of a provenance-aware graph

When to choose

  • you need a multi-temporal, provenance-aware graph as a source of truth
  • you want AI agents to automatically ingest, reconcile, and maintain data
  • you need semantic type contracts shared across systems and AI agents
  • you want to model and simulate concurrent processes (Petri nets, world models)

When to avoid

  • you just need a simple relational or document database
  • you want a lightweight embedded graph library rather than a full platform
  • you need a mature, widely-adopted product with a large external contributor community
  • you require a permissive standard open-source license (license is non-standard)

Facets

application · maturity active

database type-system search-engine agent-framework simulation nlp web-framework databases artificial-intelligence simulation self-hosted developer-tools self-hosted rust cross-platform knowledge-graph semantic-types bitemporal multi-tenant process-graph world-models entity-extraction data-integration graph-engine hashql semtype petri-net decision-support graph-processing knowledge-graphs data-engineering web-server typescript docker

9 sources

Member repositories

RepositoryRoleHealth v2
hashintel/hashmain99

For agents

markdown · JSON · MCP: product_card(name="hashintel/hash")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem