rohitg00/agentmemory
GitHubTired of your AI coding agents forgetting everything between sessions? Agent Memory solves exactly that — providing persistent memory infrastructure so your AI companions remember context, decisions, and learned patterns across every interaction. With nearly 4K stars and battle-tested benchmarks backing it up, this is the go-to solution for developers building AI agents that actually get smarter over time.
Teams whose requirements match this repository’s core capability.
Review deployment and security evidence before production adoption.
What matters before you adopt it
Security evidence without the noise
Trust remains a decision signal; CVEs and scanner evidence explain what is driving the risk.
View trust evidence & security findings▼
Architecture from code30 modules · 60 edges▼
Modules and dependency edges extracted from repository code. This is code evidence, not README inference.
Architecture evidence details
flowchart TD
%% @agentmemory/agentmemory — high-level architecture (DRAFT, refine me)
n0["(root) · 2 files"]
n1["__mocks__ · 1 file"]
n2["benchmark · 7 files"]
n3["eval · 8 files"]
n4["examples · examples · 2 files"]
n5["integrations · 6 files"]
n6["packages/mcp · 1 file"]
n7["plugin · 16 files"]
n8["scripts · scripts · 3 files"]
n9["src · 9 files"]
n10["src/cli · 37 files"]
n11["src/eval · 5 files"]
n12["src/functions · 65 files"]
n13["src/health · 2 files"]
n14["src/hooks · hooks · 16 files"]
n15["src/mcp · 6 files"]
n16["src/prompts · 7 files"]
n17["src/providers · 21 files"]
n18["src/replay · 2 files"]
n19["src/state · 13 files"]
n20["src/telemetry · 1 file"]
n21["src/triggers · 2 files"]
n22["src/utils · utility helpers · 1 file"]
n23["src/viewer · 2 files"]
n24["test · tests · 162 files"]
n25["website · 29 files"]
n2 --> n9
n2 --> n12
n2 --> n17
n2 --> n19
n8 --> n10
n8 --> n15
n9 --> n10
n9 --> n11
n9 --> n12
n9 --> n13
n9 --> n15
n9 --> n17
n9 --> n19
n9 --> n20
n9 --> n21
n9 --> n23
n11 --> n9
n11 --> n19
n12 --> n9
n12 --> n11
n12 --> n16
n12 --> n18
n12 --> n19
n12 --> n20
n12 --> n22
n13 --> n9
n13 --> n19
n15 --> n9
n15 --> n19
n17 --> n9
n18 --> n9
n18 --> n19
n19 --> n9
n19 --> n12
n20 --> n9
n21 --> n9
n21 --> n11
n21 --> n12
n21 --> n13
n21 --> n17
n21 --> n19
n21 --> n23
n23 --> n9
n24 --> n3
n24 --> n5
n24 --> n7
n24 --> n9
n24 --> n10
n24 --> n11
n24 --> n12
n24 --> n13
n24 --> n14
n24 --> n15
n24 --> n16
n24 --> n17
n24 --> n18
n24 --> n19
n24 --> n21
n24 --> n22
n24 --> n23
class n4 docs
class n8 infra
class n22 shared
class n24 test
class n14 ui
classDef docs fill:#9d7660,color:#ffffff,stroke:#7c5d4c
classDef infra fill:#b35c00,color:#ffffff,stroke:#8f4a00
classDef shared fill:#79706e,color:#ffffff,stroke:#5d5654
classDef test fill:#499894,color:#ffffff,stroke:#397975
classDef ui fill:#4e79a7,color:#ffffff,stroke:#3a5b80Nearby repositories worth comparing before adoption.
🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity, tool usage, and subagent orchestration, providing live analytics, a Kanban status board, status notifications, a cute buddy, & an interactive web UI/MacOS/Windows native app.
A local open-source Frieren desktop companion for monitoring local and remote Pi, Codex, Claude Code and Cursor sessions.
Stash is here to solve one of the biggest headaches in AI agent development — memory. If you've ever built an AI agent, you know the struggle: every conversation starts from scratch, context gets lost, and you end up stuffing giant prompts just to keep things coherent. Stash gives your agents a persistent memory layer backed by Postgres, so they can remember episodes, facts, and working context across sessions. Plus, it ships as a single self-hosted binary with an MCP server included — no cloud, no vendor lock-in, just pure dev-friendly tooling that actually works.