KarLex AI releases Graphicle to give coding agents local code graphs and memory
KarLex AI has released Graphicle, an open-source tool written in Rust that provides coding agents with project memory and a local code graph. The software is released under the Apache-2.0 license and serves as a native port of Safi Shamsi's Graphify, adding memory management, session capture, and a local web interface.
Key points
- KarLex AI launched Graphicle, an Apache-2.0 licensed Rust port of Graphify featuring code graphs and memory for coding agents.
- The tool connects via MCP to agents like Cursor and Claude Code, running locally using tree-sitter without mandatory external API calls.
- In a Kubernetes benchmark of 31,000 files, Graphicle completed code-only extraction in 3 minutes 18 seconds versus Graphify's 26 minutes 38 seconds.
The tool operates locally on macOS and Linux without requiring accounts, telemetry, or API keys for core graph operations. Graphicle integrates with coding tools such as Claude Code, Cursor, and Codex through the Model Context Protocol (MCP). It tracks repository structure using tree-sitter, links reviewed decisions to specific functions, and provides agents with cited code excerpts bounded by token budgets. KarLex AI reports that in an exploratory test indexing Kubernetes (31,000 files), Graphicle finished in 3 minutes 18 seconds compared to 26 minutes 38 seconds for Graphify 0.9.88 on the same 16-CPU Linux hardware.
Graphicle stores all graphs and past sessions in a local SQLite file. While basic code analysis runs without an AI model, generating natural language answers or indexing non-code documents requires a local or cloud-based model. A commercial team edition is currently in private preview.
Show HN: Graphicle, a Rust port of Graphify with memory for coding agents
github.com · 14 October 2026Loading the full article…
This text was published by github.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
1source- Hacker News discussion · 41 pointsnews.ycombinator.com
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Microsoft Copilot AI predicts Chainlink could reach $200–$350 by early 2027 · 1 src
- OpenAI introduces Dots agent for asynchronous task delegation · 2 src
- Anthropic adds OpenTelemetry trace export to Claude Platform for debugging and monitoring · 2 src
- The reason AI 'cannot see internal company information' is that it is not connected — MCP is a common port for connecting Claude to external tools · 1 src
- Linus Torvalds uses Anthropic's Claude Code to draft Linux kernel changes · 1 src
Comments
via GitHub Discussions