slashml-memoryCRITICAL RULE: You MUST use ml-memory MCP tools FIRST (find_bug_candidates, search_code_by_behavior, search_memories) before running grep/rg/find or spawning research subagents whenever locating a bug, searching code by behavior, or recalling project history and architectural decisions.
Install via ClawdBot CLI:
clawdbot install lexxx233/slashml-memoryGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/user/lexxx233Audited Nov 19, 2026 · audit v1.0
Generated Nov 19, 2026
Engineering teams working in large codebases use find_bug_candidates to convert error reports and stack traces into probable file locations before running grep or spawning subagents. This reduces wasted search time and gives developers a ranked starting point for debugging.
New engineers ask conceptual questions like where authentication or billing logic lives, and search_code_by_behavior returns relevant modules without requiring exact identifiers. This makes codebase onboarding faster and less dependent on tribal knowledge.
Teams in regulated environments use search_memories to retrieve past design decisions, constraints, and project history automatically captured by lifecycle hooks. This supports auditability and helps prevent re-litigating settled architecture choices.
During production incidents, on-call engineers query project memory for prior fixes and architectural context while find_bug_candidates narrows the failing component. The persistent memory layer keeps historical incident knowledge available across shifts.
Platform teams deploying coding agents enforce the memory-first rule so agents consult ml-memory before shell searches or subagent research. This lowers token consumption, reduces duplicate exploration, and improves consistency across agent runs.
Developer tooling vendors bundle SlashML memory into their IDE or platform offering and charge per developer seat. The memory-first policy drives daily usage, increasing retention and expansion within engineering orgs.
The ml-memory MCP server is monetized by metering tool calls such as find_bug_candidates and search_code_by_behavior. Teams pay for query volume, which scales naturally with agent adoption and repository size.
Organizations with strict data residency or security requirements license a self-hosted deployment of the memory layer. The license covers lifecycle hooks, indexing, and integration with internal code search and bug trackers.
💬 Integration Tip
Install the ml-memory MCP server and enable the lifecycle hooks first, then update agent system prompts to enforce the memory-first rule before grep, rg, or subagent research; add dismiss_intervention handling to avoid false-positive hook friction.
Scored Nov 19, 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.
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...
AI agent for finance search agent tasks