Memoh

Memoh is a self-hosted, always-on AI agent platform that runs multiple independent bot instances in containers with persistent long-term memory. It provides a web UI and integrates with multiple messaging channels (e.g., Telegram/Discord/Feishu/Matrix/WeChat/Email), supports tool use including MCP, and includes capabilities like browser automation and scheduled tasks.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai agents self-hosted containers memory mcp telegram discord matrix web-ui
⚙ Agent Friendliness
44
/ 100
Can an agent use this?
🔒 Security
51
/ 100
Is it safe for agents?
⚡ Reliability
31
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
60
Error Messages
0
Auth Simplicity
40
Rate Limits
20

🔒 Security

TLS Enforcement
80
Auth Strength
45
Scope Granularity
40
Dep. Hygiene
50
Secret Handling
40

README indicates a web UI and an ACL/access-control concept, plus OAuth for model/provider connections. However, it also reveals default credentials (admin/admin123) and does not provide details on API auth for programmatic access, TLS/HTTPS enforcement specifics, secret handling practices, or token scope granularity. Because it orchestrates containers, external channels, and tool execution, deployments should be hardened and audited.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You want a self-hosted multi-agent system with persistent memory and chat/channel integrations, and you are comfortable operating Docker/containerized infrastructure.

Avoid When

You cannot provide/mange required credentials for external channels/providers or cannot audit/adapt the deployment security settings (since detailed security controls are not shown in the provided README).

Use Cases

  • Personal or small-team assistant(s) that remain online and retain memory
  • Multi-bot setups where each bot has isolated state/files and its own memory
  • Integrating chat interfaces across many platforms with a unified agent experience
  • Tool-augmented agents via MCP for external services/automation
  • Automated recurring tasks and autonomous periodic behaviors
  • Lightweight self-hosted 'home agent' style deployments

Not For

  • Production deployments requiring a formally specified public API contract (OpenAPI/SDK) without further documentation review
  • High-assurance environments that need strong, clearly documented enterprise-grade security guarantees without auditing
  • Users who cannot run and maintain Docker/container infrastructure
  • Agents that require fine-grained, documented per-endpoint authorization or organization-wide identity controls

Interface

REST API
Yes
GraphQL
No
gRPC
Yes
MCP Server
Yes
SDK
Yes
Webhooks
No

Authentication

Methods: Web UI login (default username/password mentioned in README) Provider OAuth for some model/providers (described at feature level)
OAuth: Yes Scopes: No

README indicates 'Access Control' via priority-based ACL rules and per-bot model/provider OAuth, but it does not document authentication mechanisms for the core REST API endpoints or whether per-scope tokens exist.

Pricing

Free tier: No
Requires CC: No

No pricing page/tier details provided in the supplied README.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Self-hosted deployment requires correct container/network configuration; failures may look like agent/tool errors.
  • Memory and tool providers may depend on external services (LLM providers, Qdrant/Postgres, MCP tool servers).
  • Default web UI credentials are insecure for real deployments (admin/admin123).

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Memoh.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6428
Packages Evaluated
19975
Need Evaluation
586
Need Re-evaluation
Community Powered