meta-harness
265stanford-iris-lab/meta-harness
Skill Claude CodeCodex
Run one iteration of memory system evolution. Called by metaharness.py or interactively via /meta-harness.
20,034 tagged Memory and context, measured the same way as everything else here.
Browse within: agent-memory 179ai-memory 117knowledge-graph 79local-first 78knowledge-base 57knowledge-management 55obsidian 54context-engineering 50embeddings 40context-management 39gemini-cli 36copilot 32coding-agent 28markdown 27
stanford-iris-lab/meta-harness
Skill Claude CodeCodex
Run one iteration of memory system evolution. Called by metaharness.py or interactively via /meta-harness.
Skill Claude CodeCodex
Before answering a substantive question, quietly check whether the user has already resolved this question in the past.
Skill Claude CodeCodex
Weekly self-audit playback. Surface patterns from the user's past week that they probably cannot see themselves.
Plugin Claude Code
Conversation memory for AI assistants — record, transcribe, search meetings and voice memos. 22 skills + 1 agent + 2 hooks.
krusemediallc/arcads-claude-code
Cursor rule Cursor
Load project memory from MASTERCONTEXT.md and keep it updated after substantive work.
Plugin Claude Code
Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically.
Instructions file
Instructions for BayramAnnakov/claude-reflect, covering claude.md, project overview, architecture, data flow and memory targets (full hierarchy).
Skill Claude CodeCodex
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
Command
Discard queued learnings without processing.
Command
View the learnings queue without processing.
mnemox-ai/tradememory-protocol
Skill Claude CodeCodex
AI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.
mnemox-ai/tradememory-protocol
Plugin Claude Code
Persistent memory + autonomous strategy evolution for AI traders. 200+ trading MCP servers execute. None remember. TradeMemory does.
mnemox-ai/tradememory-protocol
MCP server Claude CodeCodexCursor +2
Decision audit trail + persistent memory for AI trading agents. SHA-256 tamper detection, outcome-weighted recall, strategy evolution via MCP. Runs locally from the tradememory-protocol Python package. Needs 2 environment variables to run.
mnemox-ai/tradememory-protocol
MCP server Claude CodeCodexCursor +2
Decision audit trail + persistent memory for AI trading agents. SHA-256 tamper detection, outcome-weighted recall, strategy evolution via MCP. Runs locally from the tradememory-protocol Python package.
Plugin Claude Code
Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.
Plugin Claude Code
Evidence-based learning engine: first-principles curricula, generation-first Socratic tutoring, free-recall verification with receipts, FSRS-scheduled memory, and interactive explorable artifacts. Learn anything; keep it.
Skill Claude CodeCodex
Search the user's local Pensieve screenshot archive by text, app, or time range. Use when the user asks to find a screenshot ("find that thing I looked at last week", "show me when I was working on the Mastra integration", "find screenshots of the YouTube video about X"), or to locate a specific moment in time across…
Hook Claude Code
Runs before the context is compacted, running an inline shell check. From mbailey/voicemode.
Skill Claude CodeCodex
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
Skill Claude CodeCodex
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
Skill Claude CodeCodex
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.
Skill Claude CodeCodex
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
Plugin Claude Code
Repository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.
Command
A command that rebuilds RepoBrain's knowledge base for the current workspace. RepoBrain is a tool that keeps searchable project information for an agent.
At most 3 mods per repository are shown here — the rest are on their repository pages: