mimirSelf-hosted persistent memory for OpenClaw agents via Mimir MCP — 23 tools, hybrid search, AES-256 encryption, zero external dependencies
Install via ClawdBot CLI:
clawdbot install tcconnally/mimirGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses system directories or attempts privilege escalation
sudo mvCalls external URL not in known-safe list
https://github.com/Perseus-Computing-LLC/mimir/releases/latest/download/mimir-liAudited Sep 10, 2026 · audit v1.0
Generated Sep 10, 2026
A development team runs an OpenClaw agent that assists with a large codebase across many weeks. Mimir stores architectural decisions, coding conventions, and incident postmortems as encrypted memories, recalling the right context per repository via hybrid keyword and semantic search without leaking code context to third-party clouds.
A wealth management or legal firm uses OpenClaw agents to assist advisors in client interactions, requiring durable note-taking, decision journals, and proactive recall before calls. Mimir's AES-256-GCM encryption and fully local deployment satisfy data residency and confidentiality obligations where cloud memory services would be disallowed.
Manufacturing or energy operators deploy OpenClaw agents on Raspberry Pi class hardware in disconnected plants. Mimir's single ~8MB Rust binary, no external dependencies, and stdio MCP integration allow persistent maintenance knowledge, equipment histories, and shift journals to survive restarts without any cloud connectivity.
Clinical research teams use OpenClaw to track study decisions, protocol deviations, and literature notes over multi-year trials. Mimir's knowledge graph linking, journal timeline, and Ebbinghaus decay help surface the most relevant prior findings while archiving stale ones, with encryption at rest protecting sensitive patient-adjacent context.
Government agencies run OpenClaw agents that must retain institutional memory across staff turnover while meeting strict sovereignty rules. Mimir's zero external dependencies, vault export to Obsidian markdown for auditability, and conflict detection support transparent, auditable, fully on-premise knowledge management.
Mimir's core binary remains free and MIT-style licensed for individual developers, while Perseus Computing sells paid enterprise add-ons such as multi-user key management, SSO-backed dashboards, centralized audit exports, and SLA-backed support contracts. This mirrors successful infrastructure projects that monetize compliance and operations rather than the core capability.
Rather than hosting data, the vendor offers paid installation, configuration, encryption-key ceremony, dashboard hardening, and ongoing maintenance for customers who must keep data inside their own perimeter. This suits regulated industries that cannot use SaaS memory products but still want expert deployment.
Free Agent Memory plugin is distributed through OpenClaw's skill registry and model context protocol directories to drive adoption, with monetization through premium content packs, partner integrations (e.g., vetted LLM endpoints, observability tools), and referential hosting of a certified consultant directory.
💬 Integration Tip
Start by installing Mimir as a local binary and setting MIMIR_ENCRYPTION_KEY before writing any memories, since key rotation later is painful. Then add a small set of high-value memories first (architecture decisions, conventions) and test mimir_recall_when and mimir_cohere grooming before scaling to long-term workloads.
Scored Sep 10, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...