Skip to content
@Graphicle-AI

Graphicle-AI

README.md

Graphicle. Maps your code. Remembers your project. Code graph and memory for your coding agents, in one Rust program.

Repository  ·  Quick start  ·  Docs  ·  Benchmarks  ·  Discussions

Graphicle maps your code and remembers your project, for you and your coding agents. It builds a graph of your repository (files, functions, classes, calls and imports) and keeps your documents, decisions and past agent sessions word for word, so answers come with their sources. One command, graphicle, runs it all, and everything it stores stays on your machine.

brew install graphicle-ai/tap/graphicle
cd your-repo && graphicle setup

Setup builds the code graph, connects the coding agents it finds (Claude Code, Codex, Cursor, VS Code and Claude Desktop) and lists every file it changes. Then ask your agent to "use graphicle to find where failed requests are retried", or run graphicle ask in the terminal. It runs on macOS and Linux, with a Windows preview; docs/install.md has the install script, the release archives and building from source.

One map of your code
Search the graph, explain a symbol, trace the path between two symbols and see what depends on a change. The engine is a Rust port of Graphify. 		Memory with sources
Recall returns cited excerpts without calling a model. Agents can propose memories that quote their sources, and a person approves each one.
Built for agents
MCP for Claude Code, Codex, Cursor, VS Code, Claude Desktop and any other MCP client, with session capture for Claude Code and Codex. 		Local first
No account and no telemetry. Nothing goes to a model unless you set one up (every case).

Also built in: one MCP server, graphicle mcp, with the code-graph tools under Graphify's tool names (such as query_graph and shortest_path) next to the memory tools; reviewed memories tied to the functions they are about (a memory goes stale when its function changes; edits elsewhere in the file usually leave it current); and recall across the repositories of a workspace (graphicle context --workspace).

Measured in the open

Two bar charts comparing Graphicle with Graphify 0.9.91 (Python) on 13 codebases. Left, speed: Graphify 0.9.91's time divided by Graphicle's for a code-only extract, highest first: kubernetes 22.7×, rails 7.0×, flask 6.9×, prometheus 6.6×, react 6.2×, scikit-learn 6.1×, pandas 5.8×, vscode 5.4×, ripgrep 5.3×, tokio 5.1×, redis 4.3×, next.js 4.0×, spring-boot 3.3×. A line on each bar spans its 3 operations (code-only extract, priming update and update with no change). Graphicle took less time in all 39 measurements and in every run, 3.0× to 22.7× less. Speed label: Graphicle's 0.1.1 memory engine (a pre-release build) against Graphify 0.9.91 on the same machine, 3 CPUs and 8 workers each, one session per program, 15 Oct 2026; median of 3 runs (1 for Kubernetes and VS Code). The graphs differ slightly: node counts within 4.7%, edge counts within 2.0%. Right, peak memory: Graphicle's peak divided by Graphify 0.9.91's peak for a code-only extract, lowest first: ripgrep 0.31×, flask 0.37×, pandas 0.38×, redis 0.39×, tokio 0.40×, scikit-learn 0.41×, prometheus 0.43×, react 0.50×, next.js 0.51×, vscode 0.52×, kubernetes 0.76×, rails 0.77×, spring-boot 0.94×. Lower in all 39 measurements, at 0.29× to 0.97× of Graphify's peak, on a pre-release memory build whose graphs differ from Graphify's; Graphicle's peak RSS or PSS, whichever is larger, against Graphify's peak PSS. A build of the merged 0.1.1 source stayed below in the 5 measurements rechecked. Speed and memory tables and method: docs/benchmarks.md.
  • Speed: on 13 codebases, a pre-release build of Graphicle 0.1.1's engine took 3.0 to 22.7 times less time than Graphify 0.9.91 in all 39 measurements (same machine, 3 CPUs each). The graphs differ slightly: node counts within 4.7%, edge counts within 2.0%.
  • Memory: a later pre-release build used less peak memory than Graphify 0.9.91 in all 39 measurements, from 0.29 to 0.97 times its peak; its graphs differ from Graphify's too.
  • Coding agents: with Claude Code and Opus 5.5, Graphicle ties plain Claude Code (grep) on accuracy in every test. On Graphify's own showcase corpus, the 0.1.1 agent defaults (a pre-release build) found 99.2% of the facts, against 94.7% for plain Claude Code (a tie) and 87.8% for Graphify 0.9.91, with fewer tokens than Graphify.
  • Parity: the code-graph engine is checked by running Graphify's own tests against it and comparing the results with the pinned Graphify release it follows. The upstream test files that are not run yet are listed with the reason each is not run.
  • Agent memory: seven memory systems and a build of Graphicle answered the same questions on three development sets, with one open model as every system's reader and judge (a proxy evaluator).

Every result, with its labels and caveats, is in docs/benchmarks.md, including the ties and the results that did not favour Graphicle.

Open source

Graphicle Core is free and open source under the Apache License 2.0. Contributions are welcome with a DCO sign-off (CONTRIBUTING.md). The code-graph engine is adapted from Graphify, credited in NOTICE. A commercial edition for teams is in private preview: start a discussion.

Talk to us

Graphicle is made by KarLex AI logo KarLex AI, Inc. Other product names are trademarks of their owners; no affiliation or endorsement is implied.

Popular repositories Loading

  1. graphicle graphicle Public

    Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.

    Rust 238 12

  2. homebrew-tap homebrew-tap Public

    Homebrew tap for Graphicle: brew install graphicle-ai/tap/graphicle

    Ruby

  3. .github .github Public

    Graphicle-AI organisation profile and community files

Repositories

Showing 3 of 3 repositories

Top languages

Ruby Rust

Most used topics

Loading…