project
1249Cursor rule Cursor
OpenLeukemia project instructions.
12,529 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Cursor rule Cursor
OpenLeukemia project instructions.
Plugin Claude Code
Bundles 4 skills, 1 hook · 158 tokens together
Keep AI project memory small, in git, and shared across tools. Teaches Claude the retrieval-first .ai/ contract, checks bank health at session start, and adds doctor, compact and init commands.
Plugin Claude Code
Bundles 1 skill, 1 command, 2 hooks · 165 tokens together
Hooks and an agent skill that make an agent use CPersona's memory at the right moments: look before the first action and before each answer, store as it goes, and restore the task after the conversation is compacted. Connect the CPersona MCP server separately.
Skill Claude CodeCodex
Orchestrate Butler MCP for multi-agent coordination, persistent memory, and cross-session continuity.
Skill Claude Code
Use atrib as the verifiable substrate for memory, reasoning, and getting sharper over time, not as instrumentation that observes you from the outside. atrib gives the agent two cognitive verbs: attest (write: sign an observation, mark a past record's importance, or supersede a prior position) and recall (read: look up…
Skill Claude CodeCodex
Design recurring knowledge-base update loops for Obsidian-style vaults, project wikis, second-brain folders, and research notebooks. Use when setting up automated source ingestion, daily reflection, meeting-note processing, health checks, state cursors, runbooks, scheduler prompts, or validation gates for a maintained…
Skill Claude CodeCodex
NodeSpace is context infrastructure for AI-native development — a local-first knowledge graph running on this machine.
seongjaeryu/bindly-claude-code
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 20 tokens together
Knowledge completion layer for Claude Code - finish your thoughts and make them reusable across sessions and agents.
Plugin Claude Code
Bundles 27 skills · 808 tokens together
Secure memory + persistent context + skill-admission gate for Claude Code. HMAC-chained toolcalls + outcomes, per-agent HKDF subkey isolation, Postgres RLS, work-stealing task queue, MemGPT-style persistent memory, Agent Notebook Model (Read→Summary redirect), and v0.26.0+ Anthropic-style filesystem skills with AST.
Plugin Claude Code
Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.
Plugin Claude Code
Bundles 5 skills, 3 agents, 18 hooks, 1 MCP server · 194 tokens together
Deterministic, inspectable, governed context for Claude Code through public hooks and MCP.
Skill Claude CodeCodex
Synchronize code assistant memory and consolidate memory across Claude Code, Codex CLI, Gemini CLI, Antigravity, Cursor, and Windsurf. Use when users want shared provider memory, global memory sync, memento sync, memory cleanup, or multi-assistant context portability.
Skill Claude CodeCodex
Finish a PAI→Soma migration by placing PAI's imported life-OS content correctly: keep the Purpose compartment as a lean 4-field distillation, promote the rich imported categories (beliefs, mental models, decision frames, challenges, lessons) into Soma memory as recall-able notes, and protect the curated purpose.md…
sunil-goyal-1502/project-memory
Plugin Claude Code
Bundles 11 skills, 2 agents, 1 MCP server · 151 tokens together
Automatic project decision and research capture with cross-tool context sync.
Plugin Claude Code
Bundles 2 skills · 173 tokens together
Turn any folder into your second brain. Persistent memory, daily routines, meeting intelligence, and a proper voice + ICP profile — all inside an Obsidian-compatible vault.
Skill Claude CodeCodex
Use when Hermes needs durable project or personal memory through the local hypermnesic CLI: retrieve prior context, think through related notes, resolve entities, inspect writable folders, capture notes, or preview guarded writes.
Plugin Claude Code
Bundles 8 skills, 8 commands · 1,094 tokens together
Persistent project memory for AI agents + documentation auditor - evidence-based detection of doc rot, powered by Obsidian vaults.
Plugin Claude Code
Bundles 13 skills, 8 commands, 9 agents, 4 hooks · 4,081 tokens together
Adaptive toolkit that learns your patterns and provides personalized guidance. Auto-captures observations via hooks.
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "obsidian" as configured in dbmcco/obsidian-mcp. Runs /Users/braydon/projects/experiments/mcp/obsidian_mcp/dist/index.js with node. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Semantic knowledge infrastructure for Claude Code agents - AI-powered messaging with vector search and intelligent ranking. Runs locally from the claude-slack npm package.
Plugin Claude Code
Bundles 1 skill · 33 tokens together
Personal AI memory — gives every AI agent shared, persistent memory of you. Profile, tables, semantic search, and a knowledge graph.
Bobby-cell-commits/open-brain-server
MCP server Claude CodeCodexCursor +2
Graph-structured MCP memory server. 37.2% LongMemEval. Auto dedup, themes, decay, synthesis. Remote server at {supabase_project_ref}.supabase.co.
MCP server Claude CodeCodexCursor +2
Deterministic context selection for AI coding agents. Local memory that compounds across sessions. Runs locally from the @codeledger/cli npm package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 209 tokens together
An MCP server for semantic search and connection-discovery across your own Apple Notes — hybrid search, Swanson-ABC bridges, entity threads, and cited synthesis over everything you've written.
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: