Open sourcePython · ≈138k stars · Apache-2.0
Graphify
A /graphify skill that turns a codebase, docs and schemas into a queryable knowledge graph.
Graphify turns a codebase and its docs, SQL schemas, configs and PDFs into a knowledge graph that agents can query. It installs from pip and adds a /graphify SKILL.md to the agent's skills folder, and it hooks into the agent's tool calls in Claude Code, Codex and others.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsParses code locally and deterministically with tree-sitter: no LLM call, and nothing leaves your machine.[1]
- DocsEvery edge is tagged EXTRACTED or INFERRED, so agents can tell what was read directly from what was resolved.[1]
- DocsThe vendor's benchmark reports LOCOMO recall@10 of 0.497 against mem0's 0.048 with zero LLM credits, though supermemory beats it on LOCOMO QA accuracy (49.7% vs 45.3%).[1]
- MetadataApache-2.0, with very frequent releases (v0.9.97 on 2026-10-27).[1]
Cons
- User reportsA user who tested it found it returns lots of structured output that current models and harnesses are not set up to use well.[1]
- User reportsCorrectness bugs: node IDs drop file extensions so distinct files collide (open), and Gemini silently skipped most files in an oversized chunk (since closed).[1][2]
- User reportsCodex hook integration has broken: a PreToolUse failure, and Codex rejecting additionalContext (still open).[1][2]
- MetadataAbout 725 open issues, and the README leads with an upsell to the hosted Graphify Cloud (14-day trial).[1]
- Best for
- Agents navigating large or unfamiliar repos that benefit from a local, queryable code graph instead of repeated grep.
- Watch out for
- Docs, PDFs and media still go through a model, and graph quality depends on the language parser.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
Neighbours on the workbench
MDX · ≈307k stars · MIT
obra/superpowers
An agentic skills framework and software methodology that works.
Maintained by Jesse Vincent (obra)
Shell · ≈306k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
JavaScript · ≈292k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- Graphify-LabsOrganisation
Built on · 2
- Claude CodeProject
- CodexProject
Sources
Verified Oct 29, 2026