Mink026

Mink026 / Engram

Public

基于 Planner–Manager–Executor 的文本 Agent；Executor 支持 YAML / Python 高度自定义；可选 Neo4j+Graphiti 记忆图谱；FastAPI + React。

13
0
100% credibility
Found Mar 25, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Engram is a text-based chat app featuring an AI agent that breaks down queries into planned steps, maintains session history, and optionally displays conversation memories as an interactive graph.

How It Works

1
🔍 Discover Engram

You find Engram, a friendly chat companion that remembers your talks and shows them as a memory map.

2
💾 Get the files

Download the simple folder to your computer, like grabbing a new app.

3
🔌 Link smart brain

Tell it which AI helper to use so it can understand and respond cleverly.

4
🚀 Open the chat

Start the window and see your personal chat space light up instantly.

5
💬 Start talking

Type a message and watch it plan steps, fetch info, and reply as you type.

6
🗺️ View memories

Switch to the map tab to see your conversations drawn as connected ideas.

✅ Smart buddy ready

Enjoy chats that remember details, plan ahead, and feel like a real helper over time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 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 Engram?

Engram is a Python-based text agent that breaks user queries into planned tasks via a Planner-Manager-Executor flow, delivering structured responses through a FastAPI backend and React frontend. It offers streaming chat sessions that persist in SQLite or Postgres/MySQL, with an optional Neo4j+Graphiti memory graph to track conversation entities and episodes. Drawing from the engramm definition—a brain's memory trace—this setup lets you build persistent, graph-backed dialogues without wiring up everything from scratch.

Why is it gaining traction?

Its YAML-configurable executors and Python extensions make role specialization dead simple, like swapping in researcher or analyst behaviors without redeploying. The full-stack quickstart with uv sync and npm run dev gets you chatting in minutes, supporting any OpenAI-compatible LLM for engram deepseek experiments. Devs dig the SSE-streamed plan visibility and embeddable graph viewer, standing out from bare LangGraph setups by bundling UI and persistence.

Who should use this?

AI prototype builders testing multi-step agents with tools like time queries or calculators. Researchers exploring neo4j+graphiti for engrams in chat histories, especially engram github deepseek workflows. Small teams needing a customizable chat UI faster than rolling their own FastAPI+React stack.

Verdict

Grab it for agent POCs—solid docs and env-driven setup shine despite 13 stars and 1.0% credibility signaling early maturity. Lacks tests and broad adoption, so fork for production; otherwise, it's a quick win for engram bremen-style memory experiments.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.