TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. 2026.09.19
  3. Memoh

Memoh

A cloud computer for every agent

WHO USES ITPeople who leave research or repetitive work running with an agent, and teams juggling several at once.

Self-host

An open-source platform that gives every AI agent its own cloud computer, running even when your laptop is closed.

★ 2.4k▲ +16 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-05 no data2026-09-06 no data2026-09-07 no data2026-09-08 no data2026-09-09 no data2026-09-10 no data2026-09-11 no data2026-09-12 no data2026-09-13 no data2026-09-14 no data2026-09-15 no data2026-09-16 +52026-09-17 +112026-09-18 no datalargest one-day increase in the 14 days+11last 14 days · stars per dayhollow = no data

2,398 stars · checked on GitHub GitHub check 42 h late · incl. +6 observed via GH Archive since then · 7-day +16 observed via GH Archive (as of )

The Memoh interface showing per-agent workspaces alongside the chat view.

TESIGN TAKE

Built for the case where you hand over a long job and walk away. For a question or two, you do not need it.

SELF-HOST

AT A GLANCE

LICENSE
AGPL-3.0
USAGE
Release source if you redistribute or host it as a service.
LANGUAGE
Go
PLATFORM
web
ACTIVITY
last commit 2 days ago () · latest release [unconfirmed]
COMMUNITY
contributors [unconfirmed] · open issues [unconfirmed] · made by: [unconfirmed] Reference time unavailable
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI

A summary, not legal advice.

WHY IT MATTERS

Handing work to an agent means it needs somewhere to keep files, open the web and accumulate results. Memoh gives each agent its own workspace — filesystem, desktop, browser, network and long-term memory — that stays up when your own machine is off.

BUILD FROM THIS

  • Go under AGPL-3.0. Run the built-in agent with your own API keys, or host the Claude Code and Codex agents you already use inside a Memoh workspace, and talk to them through Telegram, Discord or the web UI.

WHO IT'S FOR

People who leave research or repetitive work running with an agent, and teams juggling several at once.

START IN 5 MINUTES

# Look at memoh.ai first, decide between self-hosting and signing up, then have your model API keys ready.

CAVEATS

  • You pay for model usage yourself, since it runs on your own API keys, and AGPL-3.0 means a modified service must publish its source.

RECEIPT

FIRST SEEN
AT SOURCE
KEPT
CREATED → FIRST SEEN
247d
WHEN FIRST SEEN
2,392 ★
SOURCES
GitHub

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 261k▲ +774MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 246k▲ +298MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 228k▲ +1,095MITpermissiveweb · cli
The Memoh interface showing per-agent workspaces alongside the chat view.
MemohA cloud computer for every agentTHIS ENTRY★ 2.4k▲ +16AGPL-3.0copyleftweb
mattpocock/skillsCARD★ 261k▲ +708MITpermissive—

ALSO WORTH SEEING

OpenHunterAILocal AI red-team workspaceOpenHunterAI's homepage, labelled "AUTHORIZED EXTERNAL SECURITY TESTING," listing its five-stage process from scope verification to reporting.Self-host
★ 306▲ +15 / 7d
An alpha-stage local workspace that runs attacker-style security assessments — strictly against public targets you own or are authorized to test.MartinLoopExecution-control CLI for coding agentsMartinLoop's homepage headline: "Watch your AI burn $5.20. Then watch MartinLoop close the loop for $2.30."
★ 208▲ +25 / 7d
Wraps a coding agent with a spend cap and a verifier, so "I'm done" comes with an evidence-backed receipt instead of just a claim.Spec KitSpec-first process for coding agentsSpec Kit docs landing page — the headline 'Build with a spec, fix a bug, or assess an idea' and the uv tool install specify-cli commandInstall to use
★ 138k▲ +265 / 7d
Makes your coding agent write the spec first, then plan, build and verify against it.HindsightNarrative map for YouTube viewersHindsight landing page: thousands of video dots grouped into issue clusters, with a central search box for a topic, creator or YouTube link.Use in the browser
★ 0▲ 1 HN
Remembers 49,411 videos, maps 22,904 by issue, traces how a YouTuber's argument changed.

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN
  3. Published on TESIGN

SAME DAY

  1. 01

    Actual Budget

    Budgeting that stays on your device

    A local-first budgeting app that keeps your finances on your own device, using envelope budgeting.

    Use in the browser
    ★ 28.9k▲ +11 / 7d
  2. 02

    Harper

    Offline English grammar checking

    An English grammar checker that runs on your own machine, so what you write never leaves it.

    Use in the browser
    ★ 15.4k▲ +14 / 7d
  3. 03

    ArcReel

    Turn scripts into short-form video

    A self-hosted workbench that turns a novel or script into characters, scenes, storyboards and finished short videos.

    Self-host
    ★ 4.7k▲ +37 / 7d
  4. 04

    OpenStock

    Track prices and set your own alerts

    An open-source dashboard for tracking stock prices, company details and personalised alerts in one place.

    Use in the browser
    ★ 14.5k▲ +71 / 7d
  5. 05

    Status Trio

    One menu bar icon for three signals

    A native macOS menu bar app that merges Wi-Fi, battery and volume into a single icon.

    Install to use
    ★ 191▲ +13 / 7d
  6. 06

    liarjs

    Check where a browser contradicts itself

    Reads what a browser says about itself, compares it with what the network actually saw, and reports every disagreement.

    Use in the browser
    ★ 214▲ +21 / 7d
  7. 07

    MemOS

    Give an AI agent long-term memory

    A memory layer for LLM agents that unifies storing, retrieving and managing long-term memory.

    For developers
    ★ 11.5k▲ +13 / 7d
  8. 08

    Coder

    Self-hosted cloud dev environments

    A self-hosted platform that moves development environments off laptops onto your own infrastructure, started on demand.

    Self-host
    ★ 14.8k▲ +31 / 7d
  9. 10

    Atlassian MCP Server

    Connect Jira and Confluence to AI tools

    Atlassian's official bridge that lets AI tools read and act on Jira, Confluence and the rest of the platform.

    Install to use
    ★ 1.1k▲ +11 / 7d