mindswap
1273MCP server Claude CodeCodexCursor +2
Local-first AI context and memory server for cross-tool coding continuity. Runs locally from the mindswap npm package.
11,848 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.
MCP server Claude CodeCodexCursor +2
Local-first AI context and memory server for cross-tool coding continuity. Runs locally from the mindswap npm package.
Cursor rule Cursor
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
Skill Claude CodeCodex
Cross-session memory and continuity CLI. Provides session memory, handoff documents, and historical session retrieval. Use at session start to retrieve context from past sessions (eywa get). Use at session end to persist a handoff document for future sessions (eywa extract). Trigger on: "session memory", "handoff"…
MCP server Claude CodeCodexCursor +2
MCP server + proxy that cuts cloud LLM costs 36-42% by indexing context locally with Ollama and giving agents precision retrieval tools instead of raw dumps. Runs locally from the context-guardian-mcp npm package.
Plugin Claude Code
Bundles 8 skills, 3 hooks · 1,057 tokens together
Local fine-tuning for your own tasks, except the one doing the training is you. A provider-neutral kit that turns scattered project criteria into distilled, invariant Lore — and operates it with seven skills: use-lore, brainstorming-lore, create-area, create-project, create-bot, save-to-lore, transmute-lore.
MCP server Claude CodeCodexCursor +2
Token-minimal, constraint-preserving context assembly for AI coding agents. Runs locally from the skeletongraph Python package.
Plugin Claude Code
Bundles 3 skills, 7 commands, 1 agent · 504 tokens together
Continuous-collaboration layer for Claude Code: living project model, outcome telemetry, event digest, and calibrated confidence. Fully local, install-once, applies to every project.
Plugin Claude Code
Bundles 2 skills, 1 command, 2 agents, 5 hooks · 260 tokens together
Persistent memory for Claude Code — automatic save/restore across compactions and sessions. Anti-patch reconcile-on-write + LLM-judged semantic de-duplication, forced PROGRESS.md handoff with per-session annotation, live PLAN.md anchor, injection observability, FTS5 search, AI-judged extraction with Haiku + local…
lyc403223157-source/knowledge-inbox
Skill Codex
A skill for saving links, social posts, videos, podcasts, screenshots, PDFs, local files, or text into an Obsidian knowledge base, a personal collection of searchable notes. The ingestion tools analyse and format the material for storage.
Skill Claude CodeCodex
Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.
Plugin Claude Code
Bundles 5 skills · 409 tokens together
Lookward — build and tend a will-driven world model (markdown, OKF-aligned) from the signal you already produce. Skills are prefixed lw-.
Plugin Claude Code
Bundles 2 skills, 5 hooks, 1 MCP server · 332 tokens together
Status-line indicator showing whether the headroom MCP context-compression is being used this session — idle until headroomcompress runs, then active with the tokens AND money it saved (priced against the session model), decaying back to idle after a quiet period. Tracks an all-time money-saved total across sessions.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 hook · 135 tokens together
Recall and reuse your past AI coding sessions as long-term memory. Searches the local sessionwiki index so the agent can find prior work, pull context, and trace which session wrote a file.
MCP server Claude CodeCodexCursor +2
Shared memory & coordination for AI coding agents — a blackboard, not an orchestrator. Runs locally from the octopus-blackboard npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "pltm-memory" as configured in Alby2007/PLTM-Claude-repost. Runs C:/Users/alber/CascadeProjects/LLTM/mcp_server/pltm_server.py with python.
Plugin Claude Code
Bundles 2 skills · 348 tokens together
Org-roam knowledge management skills.
Skill Claude Code
Audit and repair a Basic Memory knowledge tree — misplaced rendering inputs, missing or inconsistent frontmatter, notes absent from the graph, and file names that break the project convention. Use when the user asks to check, audit, clean up, or migrate existing documentation.
Skill Claude CodeCodex
Use when user mentions remembering something, asks what you know about them, references past decisions, or needs to store/retrieve personal context across sessions.
Plugin Claude Code
Bundles 1 skill · 155 tokens together
Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.
Plugin Claude Code
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
MCP server Claude CodeCodexCursor +2
Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction, sha256-verified. Runs locally from the densely Python package.
MCP server Claude CodeCodexCursor +2
Persistent memory and virtual filesystem MCP server for AI agents. Runs locally from the @memofs/mcp-server npm package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 4 skills, 6 hooks, 1 MCP server · 176 tokens together
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale.
agenerationforwordz-tech/strata
Plugin Claude Code
Persistent memory for AI assistants — runs locally on your machine. Remember every decision, debugging session, and architecture debate across sessions. One MCP server, zero cloud dependencies, works on a Raspberry Pi.
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: