proofofwork-agency

Local codebase memory for Claude Code and MCP - AST indexing, call graphs, hybrid search. 0 tool calls, 3-8x fewer tokens.

11
1
100% credibility
Found Mar 22, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Reporecall indexes codebases to provide structured context and persistent memory to AI coding assistants like Claude Code via hooks and MCP tools.

How It Works

1
🔍 Discover Reporecall

You hear about a helpful sidekick that makes AI assistants like Claude instantly understand your entire codebase.

2
📦 Set it up in your project

With one simple command, you add it to your folder and it prepares a private memory space just for your code.

3
💾 Teach it your code

Tell it to scan and remember all your files, and it quietly builds a smart map of everything inside.

4
🚀 Start the magic helper

Flip the switch to run its background service, and it stays ready to assist whenever you need.

5
🤖 Ask AI anything about your code

Chat with your AI helper, and it automatically pulls in the perfect code snippets without you lifting a finger.

6
🧠 Save special notes

Jot down key insights or rules as 'memories' that the AI remembers across sessions.

Your AI knows your code like a teammate

Now every question gets spot-on answers with full context, saving hours of hunting through files.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is reporecall?

Reporecall indexes your local codebase with AST parsing and call graphs for hybrid semantic+keyword search, delivering precise local codebase awareness without cloud uploads. The TypeScript CLI lets you init, index, and serve a daemon that injects context into Claude Code prompts via hooks or MCP tools, slashing tokens 3-8x with zero tool calls. Pair it with Ollama for fully local LLM codebase queries, acting as a local GitHub Copilot alternative.

Why is it gaining traction?

It hooks directly into Claude Code sessions and MCP servers, auto-assembling context from your local GitHub repository—no manual file reads or repeated tool calls. Benchmarks show 3-8x token savings and fast retrieval via call/call graphs, plus file watching keeps local codebase indexing fresh. Devs dig the daemon's low overhead and MCP endpoints like search_code or find_callers for instant wins.

Who should use this?

Claude Code users on mid-sized TS/JS/Python repos needing local codebase RAG for debugging flows or refactoring. Ideal for solo devs or teams running local GitHub Actions runners, local GitHub instances, or Postman local codebase tests without token bloat. Skip if you're all-in on cloud Copilot.

Verdict

Promising for Claude workflows with proven 3-8x savings, but 11 stars and 1.0% credibility signal early maturity—lean README, light tests. Try it on a side project; production needs more polish.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.