322 tagged ai-memory, measured the same way as everything else here.
Browse within: knowledge-management 108ai-assistant 94agent-memory 74agentic-workflows 61aider 61gtd 60markdown 47agent-framework 43invos 34starter-kit 34container-isolation 31persistent memory 31self-improving-ai 31knowledge-base 10
Agent
This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…
Agent
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
modeled-information-format/MIF
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
modeled-information-format/MIF
Agent
MIF Ontology Manager - Create, validate, inspect, and convert MIF ontology definition files using yq, jq, and shell scripts grounded in the MIF JSON Schema.
Agent Claude Code
Use this agent when the user needs help designing, architecting, or planning new agents or workflows. This includes: Context: User wants to create a new agent system for their project. user: "I need to build an agent that monitors GitHub PRs and sends Slack notifications" assistant: "Let me use the agent-architect to…
Agent Claude Code
Use this agent when you need to implement AI agents based on approved implementation plans. This includes: Context: User has an approved implementation plan ready. user: "I have a plan for a GitHub PR monitoring agent, can you implement it?" assistant: "Let me use the agent-implementer to execute the implementation…
Agent
Part of troth
Deep-dive codebase researcher. Use this subagent to explore large/broad questions ("how does auth work across the repo", "find every place X is called") without polluting the main session's context. Returns a dense synthesis, not raw dumps.
Agent
Part of cairn
Cairn curator map subagent — one shard in, ≤15 candidate DEC/INV JSONL out. Spawned in parallel rounds of 4 during Phase 9b-curate.
Agent
Part of cairn
Cairn curator reduce subagent — clusters all curator-map output, synthesizes the final 30-80 DEC/INV set, writes final.jsonl. Spawned once after every map subagent finishes.
Agent
Part of cairn
Optional. Use only when the operator explicitly asks for a diff review or a DEC-drafting sweep. The default close path is the AI calling cairntaskcomplete with a summary.
Agent Claude Code
Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.
Agent Claude Code
Mechanical, low-judgment work delegated by the lead — boilerplate, scaffolding, multi-file sweeps and renames, doc formatting, test fixtures, applying an exactly-specified pattern across many files. NOT for tests, logic, or anything requiring design judgment. Runs on Sonnet.
Agent Claude Code
The independent review pass on a diff or PR — ONE holistic pass over the full change (code + tests + docs together), findings ranked Blocking/Important/Minor. Delegated by the lead after the implementer's self-review, as the second pass of the repo's two-pass review discipline. Runs on Opus.
Agent
Part of krimto
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
Agent
Part of ConsiderateCoder
A Japanese-language coordinator for dividing tasks, delegating them to workers, reviewing results, and tracking progress. It is designed to direct larger jobs rather than perform research or implementation itself.
Agent
Part of ConsiderateCoder
A task-running agent for investigating, building, and checking a defined piece of work. It is given a focused brief with context, completion criteria, and a required report format.
Agent
Part of EmailingEssay
Reflection and essay writing subagent.
Agent Claude Code
You are a QA tester simulating a real human discovering and setting up Claw Kit for the first time. You've never seen this project before. Your job is to go through the entire setup and usage flow, documenting what works, what breaks, and what's confusing.
Agent
Daily autonomous agent that makes TIMPS more secure, reliable, and capable. Each session focuses on one module from the weekly rotation, produces meaningful improvements (no line-count quota), and opens a pull request for human review before merging. Pick this agent for continuous, high-quality self-improvement of…
Agent Codex
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
Agent Codex
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
Agent Codex
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
CHANGGELY/claude_codex_gemini_mem
Agent Claude Code
Use this agent when the user requests a morning report, daily summary, or overview of their GitHub activity. Trigger phrases include 'morning report', 'github report', 'daily github summary', 'what's happening on github', or 'check my github status'. This agent should be used proactively when the user starts their day…
Agent
Part of thoughtline
Specialist subagent for thoughtline memory hygiene. Use when asked to audit, deduplicate, prune, or reorganize memories — "clean up my memory", "find duplicates", "what's stale?", "auditá la base", "qué memorias podemos archivar?". Read-mostly, never deletes without explicit user confirmation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: