Gentleman-Programming/engram

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

AI agentsGo

2.1 Steady Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 25, 2026, 13:57 UTC.

Open on Seismograph Open on GitHub

About the project

Persistent memory for AI coding agents: a single Go binary with SQLite and FTS5, exposed via MCP, HTTP API, CLI, and TUI. It lets an agent store and recall decisions, bugs, and conventions across sessions.

Useful for

Connect Engram to Claude Code or Cursor via MCP so the agent remembers project context across sessions
Save a session summary with next steps before ending an agent session
Search prior decisions and fixed bugs with mem_search instead of re-investigating

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

8 stars so far today, about 17 expected by the end of the day.
GitHub Trending Go today: #17, +36 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 6,826
Today: 8 · ≈ 17 by evening
Forks: 702
Issues and pull requests: 1,416
Watchers: 37
Language: Go
License: MIT
Latest release: v2.2.0 · September 25, 2026
Created: February 16, 2026
Last push: September 25, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 25, 2026GitHub Trending Go today: #16, +36 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/Gentleman-Programming/engram.svg?lang=en)](https://gitnova.dev/en/r/Gentleman-Programming/engram)

Similar by description

0.5
friday-memory/friday
Friday is a self-hosted persistent memory layer for AI coding agents (Cursor, Claude, VS Code), running as an MCP server. It stores decisions, schemas and preferences across sessions using Mem0, ChromaDB and Neo4j.

SteadyAI agentsPython+0 stars today, ≈ 0 by evening
0.9
kharmanskyi/open-steps
A pack of skills for coding agents (Claude Code, Codex, Cursor, Gemini CLI) that rewrites their technical reports into plain language: clear summaries, verdicts and next steps for non-engineers.

CoolingAI agentsShell+3 stars today, ≈ 5 by evening
1.8
supermemoryai/supermemory
Memory and context engine for AI: extracts facts from conversations, builds user profiles, combines RAG and memory in one API, runs locally or in the cloud.

CoolingAI agentsTypeScript+6 stars today, ≈ 14 by evening
2.4
volcengine/OpenViking
Open-source context database for AI agents: stores knowledge, user memory and skills as a viking:// virtual filesystem with search and tiered context loading.

CoolingAI agentsPython+19 stars today, ≈ 38 by evening
1.9
mksglu/context-mode
An MCP server for AI coding agents that sandboxes tool output (up to 98% context reduction), persists session memory in SQLite with FTS5 search, and enforces routing across 17 platforms.

CoolingAI agentsTypeScript+9 stars today, ≈ 20 by evening
3.2
vshulcz/deja-vu
A local Go binary that indexes session history from 34 coding agents (Claude Code, Codex, Cursor, etc.) and gives them a shared memory layer via MCP. No LLM, no embeddings, works from files already on disk.

BreakoutAI agentsGo+13 stars today, ≈ 29 by evening