Memory and context

12,531 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.

neemee-mcp

3025

Paul-Bonneville-Labs/neemee-mcp

MCP server Claude CodeCodexCursor +2

MCP client library and bridge for Neemee personal knowledge management system. Runs locally from the neemee-mcp npm package. Needs 2 environment variables to run.

not rated 0 7mo ago A tokens not measured archived

tabula

3026

nikhilbhima/tabula-mcp

MCP server Claude CodeCodexCursor +2

Cross-AI personal memory. Save once in ChatGPT, recall in Claude, Mistral, Grok, or any MCP client. Remote server at www.tabula360.com.

not rated 0 3mo ago A tokens not measured

onetrueclaude-creator/mcp-contradiction-check

MCP server Claude CodeCodexCursor +2

Find where your notes disagree — contradiction detection for markdown vaults. Runs locally from the mcp-contradiction-check Python package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured original MIT

hebbian-vault

3028

onetrueclaude-creator/hebbian-vault

MCP server Claude CodeCodexCursor +2

MCP server that adds intelligent, use-adaptive search to Obsidian vaults. Your vault remembers what matters. Runs locally from the hebbian-vault Python package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured original MIT

mcp-curiosity-engine

3029

onetrueclaude-creator/mcp-curiosity-engine

MCP server Claude CodeCodexCursor +2

Surface the notes you forgot you wrote — DMN replay for markdown vaults. Runs locally from the mcp-curiosity-engine Python package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured original MIT

vault-health-mcp

3030

onetrueclaude-creator/vault-health-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Obsidian vault structural health checks. Find broken links, orphaned notes, missing frontmatter — and auto-repair them. Runs locally from the vault-health-mcp Python package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured original MIT

panella

3031

panellatech/panella

MCP server Claude CodeCodexCursor +2

Governed, self-hosted memory for AI agents. Runs locally from the panella Python package.

not rated 0 1mo ago A tokens not measured original Apache-2.0

manoma

3032

paperdavid/manoma

MCP server Claude CodeCodexCursor +2

MCP server for soul.md — your portable AI identity layer across every LLM. Runs locally from the manoma-mcp npm package. Needs 1 environment variable to run.

not rated 0 1mo ago A tokens not measured original MIT

smara

3033

smara-io/mcp-server

MCP server Claude CodeCodexCursor +2

Persistent cross-platform memory for AI agents with Ebbinghaus decay scoring. Runs locally from the @smara/mcp-server npm package. Needs 1 environment variable to run.

not rated 0 7mo ago A tokens not measured

phaedo-mcp

3034

phaedo-labs/phaedo-mcp

MCP server Claude CodeCodexCursor +2

Make AI apps answer your way, check with you before acting, and get approvals on your phone. Runs locally from the phaedo-mcp npm package.

not rated 0 4d ago A tokens not measured copy · 100% Apache-2.0

openharness

3035

philo-kim/openharness

MCP server Claude CodeCodexCursor +2

Lets AI coding agents discover and reference each other's recent sessions. Runs locally from the @freebird-ai/openharness npm package.

not rated 0 7mo ago A tokens not measured

codewatch-memory

3036

KlausAndrade/codewatch

MCP server Claude CodeCodexCursor +2

Code-aware observational memory MCP server for AI coding assistants. Runs locally from the codewatch-memory npm package.

not rated 0 8mo ago A tokens not measured

cgraphy

3037

pmgarg/cgraphy

MCP server Claude CodeCodexCursor +2

Code knowledge graph over MCP: compact, token-budgeted context for AI coding agents. Runs locally from the cgraphy Python package.

not rated 0 3mo ago A tokens not measured original MIT

pensieve

3038

praveen-ilangovan/pensieve

Skill Claude CodeCodex

The user's personal Pensieve memory — a persistent, self-organising knowledge base that survives across sessions. Use whenever the user mentions "pensieve", asks about "my streams" / "my memory" / "what have I saved", says "add this to pensieve" / "remember this" / "save this", asks "what do I know about ", or wants…

not rated 0 2mo ago A 99 tokens original MIT

mcp-bookmark

3039

preedew17/mcp-bookmark

MCP server Claude CodeCodexCursor +2

MCP server to save and search bookmarks using OpenAI RAG. Runs locally from the mcp-bookmark-server-preedew Python package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured

bsp-mcp

3040

pscale-commons/bsp-mcp-server

MCP server Claude CodeCodexCursor +2

Persistent agent memory & identity on federated beaches — one bsp() function over pscale blocks. Remote server at bsp.hermitcrab.me.

not rated 0 2d ago A tokens not measured original MIT

qmediat/gemini-code-context-mcp

MCP server Claude CodeCodexCursor +2

Gemini 2M context cache for Claude Code — persistent; repeat queries 8x faster, 4x cheaper. Runs locally from the @qmediat.io/gemini-code-context-mcp npm package. Needs 8 environment variables to run.

not rated 0 4d ago A tokens not measured original MIT

adaptive-memory-graph

3042

raskolnikovdd/adaptive-memory-graph

MCP server Claude CodeCodexCursor +2

Intelligent persistent memory graph MCP plugin for Claude — weighted, interconnected knowledge nodes that evolve through conversation. Runs locally from the adaptive-memory-graph Python package.

not rated 0 8mo ago A tokens not measured original MIT

darwin-memo

3043

rogermsc/darwin-memo

MCP server Claude CodeCodexCursor +2

Self-curating memory for LLM agents: MeMo-style external memory kept honest by survival-based selection instead of reward models or judges. Runs locally from the darwin-memo Python package. Needs 1 environment variable to run.

not rated 0 1mo ago A tokens not measured original MIT

cap-shield

3044

robinlidberg-dot/cap-shield-mcp

Skill Claude CodeCodex

Measure and reduce what an agent sends into its context. Use when an agent's context is large, when retrieval quality matters, when the user asks about token cost or context bloat, or when agent answers are wrong in ways that look like missing information rather than reasoning failure. Also use to measure compression…

not rated 0 changed 26d ago A 77 tokens original MIT

agentram-mcp

3045

seanmarkwei/agentram-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol server for AgentRAM. Persistent memory for AI agents. Runs locally from the agentram-mcp npm package. Needs 1 environment variable to run.

not rated 0 2mo ago A tokens not measured original MIT

snhp

3046

ryuxik/snhp

MCP server Claude CodeCodexCursor +2

Free game-theory negotiation advisor for agents, plus paid receipted sessions and agent memory. Remote server at api.snhp.dev.

not rated 0 1mo ago A tokens not measured original Apache-2.0

seojeom-mcp

3047

seojeom/seojeom-mcp

MCP server Claude CodeCodexCursor +2

Local-first MCP server for Claude/Codex project wiki and graph workflows. Runs locally from the @seojeom/mcp-server npm package.

not rated 0 5mo ago A tokens not measured original MIT

memory

3048

shackleai/memory-mcp

MCP server Claude CodeCodexCursor +2

Persistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool. Runs locally from the @shackleai/memory-mcp npm package.

not rated 0 8mo ago A tokens not measured original MIT