smkbarbosa

smkbarbosa / context-ia-manager

Public

Busca semântica e memória persistente para projetos Django (e qualquer projeto Python), integrado ao VSCode e Antigravity via protocolo MCP — reduzindo o uso de contexto de IA em até 98%. Inspirado no th0th, reescrito em Go com foco em projetos Django e sem dependência de runtime (binário único).

11
1
100% credibility
Found Mar 10, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

A local tool that indexes code projects for efficient semantic search and persistent memory, helping AI coding assistants retrieve relevant context without full file uploads.

How It Works

1
📰 Discover the helper

You learn about a smart tool that helps AI assistants understand your coding projects deeply without wasting time on full files.

2
📥 Get it ready

Download and install the easy program on your computer so it's all set up.

3
🔌 Turn on the magic

Run a quick start command to wake up the background helpers that do the heavy lifting.

4
📁 Pick your project

Go to your coding folder and tell the tool to prepare it for smart searching.

5
📚 Teach it your code

Let the tool scan and remember every important part of your project, making it super knowledgeable.

6
🔍 Search and save notes

Ask natural questions to find code bits instantly, or jot down key decisions to recall later anytime.

7
💡 Connect to your editor

Link it to your coding app so your AI buddy automatically gets the right project context every time.

🚀 AI knows your project perfectly

Your coding sessions speed up as the AI gives precise, tailored help using your project's own smarts, feeling like having a expert teammate.

Sign up to see the full architecture

6 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 context-ia-manager?

Context-IA-Manager is a Go-based tool delivering semantic search and persistent memory for Django and Python projects, slashing AI context usage by up to 98% via local Ollama embeddings. It indexes code, ADRs, PRDs, and plans into a SQLite store, exposing hybrid busca (semantic + keyword) through CLI commands like `ciam search "JWT auth" --type view` or MCP protocol integration with VSCode and Antigravity. Developers get precise, compressed context retrieval without dumping full files into AI prompts.

Why is it gaining traction?

Unlike generic GitHub busca panels or cloud RAGs, it runs fully offline as a single binary with no runtime deps, focusing on Django-aware chunking (models, views, serializers) and knowledge management for real projects. MCP tools like `ciam_decision_context` auto-feed AI assistants structured context—code + decisions + plans—making it a seamless context manager for local workflows. The 98% token savings hook pulls in cost-conscious teams tired of bloated prompts.

Who should use this?

Django backend devs maintaining mid-sized apps with scattered ADRs/PRDs, using VSCode Copilot or Antigravity for code gen. Python teams needing persistent recall across sessions, like recalling "UUID PK decisions" before refactoring models. Solo devs or small squads evaluating local AI boosts without vendor lock-in.

Verdict

Promising niche tool for Django context handling—excellent docs and CLI make setup painless—but at 11 stars and 1.0% credibility, it's early alpha; test on non-prod projects first. Worth a spin if MCP integration fits your stack.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.