Radar / AI infrastructure / Graphify
Graphify: turn any codebase into a knowledge graph your agent queries
A CLI plus agent skill that parses code with tree-sitter into a queryable knowledge graph of functions, classes, imports and calls, layered with docs and PDFs — no vector store.
Why it matters
Deterministic, local and explainable: every edge is tagged as extracted or inferred, and agents query the graph instead of re-reading files, cutting exploration tokens 5-10x in independent tests.
What you could build with it
A team onboarding engineers onto a large legacy codebase could build the graph once and let newcomers ask the agent questions against it, so the first week stops being a grep marathon and starts with a map of how the code actually connects.
Does it hold up?
Tested on real repos, it cuts exploration tokens 5-10x for reading unfamiliar code, but it only replaces exploration, not editing, and the docs and media pass costs model tokens.
Built with Graphify
- Graphify: Turn Any Codebase Into a Knowledge Graph (2026 Guide)diego-rodriguez · Read the README, docs and skill file at v0.9.95 to separate what runs locally for free from what costs tokens.
- Graphify: Turn Your Codebase into a Knowledge Graph Your Agent Can Queryskillstackhq · Walkthrough of the two-pass build and the three artifacts it produces: graph.html, GRAPH_REPORT.md and graph.json.
Learn more
First spotted on github: source.
More AI infrastructure
vLLM v0.34.0: extensible KV cache by default, Model Runner V2 only, and 10 new modelsThe open inference engine's latest release spans 1,061 commits from 412 contributors, adds 10 models including Mistral…infra · JEV 0.86llama.cpp v1.0.0: the local-AI engine's first stable releasellama.cpp and ggml hit v1.0.0, promising semantic versioning so breaking C API changes only arrive with major bumps.infra · JEV 0.84FreeLLMAPI: one free endpoint across 87 LLM providersA self-hosted router that puts 87 free LLM providers and 1,313 free model endpoints behind one OpenAI-compatible /v1…infra · JEV 0.73DeepSeek App API: the whole consumer app, now as developer APIsDeepSeek opened its app's capabilities through its API: web search, file parsing, URL reading, safety checks, voice…infra · JEV 0.67InferSSD: run 800B-class MoE models from an SSD on consumer hardwareWiCi's open-source inference engine streams MoE expert weights from NVMe so models larger than RAM or VRAM can run…infra · JEV 0.64TrnRT: an open LLM inference engine for AWS Trainiuminfra · JEV 0.63
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.