The archive · Developer & Business Tools · Product decision · 2025–2026
Graphify bets AI agents need code knowledge graphs, not grep; 108K stars
Safi Shamsi's /graphify skill maps codebases into queryable graphs so AI agents stop burning tokens; 108K GitHub stars, first YC company past 100K mid-batch.
Graphify Labs
What the business is
A San Francisco startup whose open-source /graphify skill (MIT, PyPI package graphifyy) turns a codebase, docs, PDFs, and media into a local, queryable knowledge graph that Claude Code, Cursor, Codex, and 20+ agents query instead of grepping, with an on-prem enterprise layer in early access.
Starting capital：$500K from Y Combinator (S26) per ROSS Index Q2 2026; no other disclosed funding.
How it started
Safi Shamsi, a published knowledge-graph researcher and author of 'The Memory Layer', founded Graphify Labs in 2025 after concluding AI agents waste tokens re-reading code. The open-source engine went from an empty repo on 2026-04-05 to ~40k stars by May 1, 2026.
What happened
Growth sustained roughly a thousand stars a day: 58k by mid-May, 73k by early July, 88,215 by 2026-07-16 (GitHub #3 trending Python), with 2.2M+ PyPI downloads in 2.5 months. ROSS Index Q2 2026 ranked it the top trending open-source startup at 74.4x star growth. Y Combinator took it into S26, and the 2026-08-24 launch page reported 108K+ stars, 5M+ downloads, 6,000+ platform signups in its first weeks, and enterprises running it in production.
How it ended up
Still running: Graphify Labs is launching the enterprise layer — an on-prem, always-updating knowledge graph with verified code review over MCP — via a 10-design-partner program before Sept 10, 2026.
Background
Graphify Labs, founded by knowledge-graph researcher Safi Shamsi, bets that AI coding assistants will pay for a parsed, queryable knowledge graph of a codebase instead of re-grepping files every session. Its open-source /graphify skill parses code locally with tree-sitter — no embeddings, no vector store, no LLM credits — and hands agents (Claude Code, Cursor, Codex, Gemini CLI, 20+ others) an interactive graph to query.
The traction was explosive: an empty repo on 2026-04-05 reached ~40k stars by May 1, 58k by mid-May, 73k by early July, and 88,215 by 2026-07-16 (GitHub #3 trending Python), with 2.2M+ PyPI downloads in 2.5 months. ROSS Index Q2 2026 ranked Graphify the top trending open-source startup at 74.4x star growth, and Y Combinator took it into the S26 batch.
By the 2026-08-24 launch page, Graphify reported 108K+ GitHub stars — the first YC company to cross 100K stars mid-batch — plus 5M+ downloads, 6,000+ platform signups in its first weeks, and enterprises running it in production. The company is now selling the enterprise layer: an on-prem, always-updating graph with verified, MCP-connected code review, offered to ten design partners before Sept 10, 2026.
What has to be true
- The wedge was the pain: agents burning 10–40k tokens re-grepping the same monorepo every session made the token-saving pitch instantly real to developers.
- Local-first, zero-LLM code parsing removed the cost objection — the graph built in about 30 seconds with no API bill, versus per-token indexing from competitors.
- The shareable graph.html made adoption viral: developers could see and share the whole codebase map in a browser, which is what lit up GitHub.
- YC timing was the credential: joining S26 mid-batch at ~100K stars made it the first YC company to cross 100K stars during the batch.
What can be applied
When AI agents become the users, the demo must be the product: Graphify's shareable graph.html and zero-cost local parse made adoption instant, and GitHub virality did what marketing would have.
Aftermath
As of 2026-08-24 Graphify Labs is live: the open-source engine has 108K+ stars and 5M+ downloads, and the company is courting ten design partners for the on-prem enterprise graph before Sept 10, 2026. Revenue is not disclosed; the $500K YC standard deal is the only disclosed capital. The open question is whether teams will pay for the enterprise layer — on-prem graph plus verified PR review over MCP — once the free skill is ubiquitous: the classic open-source-to-enterprise conversion bet.
Sources
- Launch YC: Graphify Labs: Knowledge Graph Engine for Enterprises
- Graphify Review: 88K-Star YC S26 Code Knowledge Graph
- Top trending open-source startups in Q2 2026
spotted an error? The archive wants to know.
Your turn
You just read one. Describe what you are building, and see who is betting on the same thing.
Free account · 3 free questions · no card