jambavan

A local memory and code-understanding service for coding agents, with an abstract syntax tree index, saved decisions and failures, review materials, and a graph view. An abstract syntax tree is a structured representation of source code.

In plain words
What is it for?
Use it to index a codebase, save decisions and failure records, prepare review packs, compress prompts, and inspect a local code graph.
Why use it?
It keeps repository context and past engineering decisions available locally instead of requiring agents to rediscover them or upload the code.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add beingmartinbmc/jambavan
agentmods
npx agentmods add plugins/beingmartinbmc/jambavan/jambavan
Clone the repo
git clone --depth 1 https://github.com/beingmartinbmc/jambavan

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

jambavan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/jambavan/.claude-plugin/plugin.json · 39 lines

What it actually says

{
  "name": "jambavan",
  "description": "Local-first codebase memory for coding agents: AST-aware context, durable decisions, failure records, review packs, and a local graph GUI. Twenty tools are advertised by default; write_file, patch_file, prompt compression, and bash are opt-in. Discipline protocols ship as MCP prompts rather than tools. Pre-2.0 tool names still resolve. No LLM calls, telemetry, or code upload; repository indexes and the global memory archive stay local.",
  "version": "2.0.2",
  "author": {
    "name": "beingmartinbmc"
  },
  "homepage": "https://github.com/beingmartinbmc/jambavan#readme",
  "repository": "https://github.com/beingmartinbmc/jambavan",
  "license": "MIT",
  "keywords": [
    "mcp",
    "model-context-protocol",
    "code-index",
    "tree-sitter",
    "developer-tools",
    "mcp-server",
    "llm-memory",
    "coding-agents",
    "persistent-memory",
    "prompt-compression",
    "local-first",
    "review-automation",
    "agent-memory",
    "claude-code",
    "cursor",
    "codex"
  ],
  "mcpServers": {
    "jambavan": {
      "command": "npx",
      "args": [
        "-y",
        "jambavan"
      ]
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 39 lines scan A 26d665fa2fd7

Subscribe to this mod's changes

jambavan is a plugin published in the GitHub repository beingmartinbmc/jambavan (2 stars, last pushed 26d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

claude-code-plugin

Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.

Prismer-AI/PrismerCloud · not measured

emulo

Mine real AI coding sessions into a bounded, evidence-backed personal layer.

ohad6k/emulo · not measured

engraphis

Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.

Coding-Dev-Tools/engraphis · not measured

memory-kit

Persistent memory for coding agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a system…

awrshift/agent-memory-kit · not measured

cix-cowork

cix skills for Claude Desktop & Cowork — the cix (single-repo) and cix-workspace (cross-project) guidance adapted to the cix MCP tools. Requires a self-hosted cix (CodeIndeX) server (https://codeindex.app). Skills only: no MCP server, no CLI, no hooks. Register the cix MCP server first with cix mcp install claude-de.

dvcdsys/code-index · not measured

claude-code

HaloMem organizational memory: session-start recall, session-end capture, MCP tools. Configure with HALOMEMURL and HALOMEMAPIKEY.

halofyai/halofy · not measured