This release adds 2 notable features for engineering teams evaluating rollout.
Published 25d
RAG & Retrieval
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
antigravity
claude-code
codex
gemini
graphrag
knowledge-graph
+5 more
leiden
openclaw
llm
skills
tree-sitter
Summary
AI summaryFixed Ollama VRAM exhaustion by deriving num_ctx from actual token usage.
Full changelog
What's new
Fixes
- Ollama VRAM exhaustion (#798):
num_ctxis now derived from the actual chunk size instead of hardcoded 131072. With--token-budget 8192, the old value forced Ollama to allocate 128k KV-cache slots on a 31B model — 4×128k slots by chunk 4 caused OOM. New formula:min(input_tokens + output_cap + 2000, 131072)so an 8k chunk gets ~26k instead. - Hollow-response warning improved: now mentions VRAM pressure and points to
GRAPHIFY_OLLAMA_NUM_CTX/GRAPHIFY_OLLAMA_KEEP_ALIVEenv vars as tuning knobs.
Features
graphify export callflow-html(#797): generates a self-contained Mermaid architecture/call-flow HTML page fromgraphify-out/graph.json— community sections, interactive flowcharts with zoom/pan, call detail tables, and graph report highlights.- Living architecture diagram (#800): callflow HTML now auto-regenerates on every
--watchrebuild and post-commit hook if the file already exists. Run once, stays current forever.
Upgrade
uv tool upgrade graphifyy
# or: pip install --upgrade graphifyy
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About graphify
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, OpenClaw, Factory Droid, Trae). Turn any folder of code, docs, papers, images, videos, or YouTube links into a queryable knowledge graph
Beta — feedback welcome: [email protected]