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.
Keep durable, searchable memory across sessions and agents with the local delx-memory MCP server (SQLite on this machine). Use when the user says remember this, asks what was decided before, wants context carried to a future session or another agent, or needs a handoff note. Never stores secrets or credentials.
Every agent is smart inside its own silo. Kindex lets them work together: a persistent knowledge graph that Claude Code, Codex, Gemini CLI, Antigravity, OpenCode, and Cursor all read and write.
★not rated 1
changed 5d agoA
tokens not measured
original
Local memory banks you keep — a localhost Hub UI + MCP connector for Claude. You curate titled, dated memory banks on your machine; Claude recalls them via MCP. Runs locally from the localkeep Python package. Needs 2 environment variables to run.
★not rated 1 2mo agoA
tokens not measured
originalMIT
An agent workflow that turns files and links placed in a Desktop inbox into checked, categorized notes for Obsidian, a note-taking application. It also updates section contents, a master index, and an action-oriented summary.
Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…
End-of-session self-improvement. Review the session for user corrections, steering, and reusable discoveries, then route them into global or project CLAUDE.md, auto-memory, GSD planning docs, or (rarely) a skill, with a compact preview and per-item approval before anything is written. Use when the user invokes…
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
MCP server "fastcontext-hybrid-mcp" as configured in LyuboslavLyubenov/fastcontext-hybrid-mcp. Runs locally from the fastcontext-hybrid-mcp Python package.
A local MCP server that adds an evidence store, semantic memory, a project model, and runbooks to Cursor's AI agent. Cursor is an AI-powered code editor.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Search, read, and lightly organize the user's Trilium notes via hybrid lexical+semantic query over note content. On-demand: find a note, check what's in the journal, add a label, link two notes.
Model Context Protocol server for Engrava - expose an agent memory database to any MCP client over stdio. Runs locally from the engrava-mcp Python package. Needs 3 environment variables to run.
Governed, auditable knowledge your team curates for its AI assistants, self-hostable. Remote server at mcp.kumbuka.ai.
★not rated 1 11d agoA
tokens not measured
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: