Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Recall — persistent memory for agents
MCP serversPersistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.
-
rovai-ai
Agents & frameworksDesktop and web workspace for lasting teams of coding agents, with shared conversations, task delegation, and collaborative memory.
git clone https://github.com/murray17/rovai-ai.git -
Memory for AI
MCP serversLocal codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
memory-for-ai-mcp@0.11.0 -
Mirror Memory MCP Server
MCP serversPersonal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
-
Visual Memory MCP
MCP serversLocal visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.
@putervision/vision-memory-mcp@1.4.2 -
feedback-memory
MCP serversRemembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
https://github.com/ssap-pa/self-learning-agent-setup/releases/download/v0.2.1/feedback-memory.mcpb -
sqlite-graph-memory
MCP serversRecall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.
sqlite-graph-memory@0.3.9 -
Lore Memory for Windows
MCP serversCited local coding-agent history for fresh Codex and Claude Desktop chats on Windows.
https://github.com/fayzkk889/lore/releases/download/v0.10.0-alpha.24/lore-memory-windows.mcpb -
Engram: AI memory you can edit in Obsidian
MCP serversShared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.
-
kana
SkillsLightweight, untracked, and self-evolving terminal AI companion. Zero telemetry, durable memory, bidirectional synergy, and native TUI.
git clone https://github.com/longyijdos/kana.git -
Configure Memory
MCP serversBring your saved preferences, project decisions, and useful context into your next AI conversation.
-
Run Memory
MCP serversCheckpoint and resume for AI agent runs, so crashed runs pick up where they left off.
-
OneSelf
SkillsOne self. One context. Every AI.
git clone https://github.com/ptonlix/OneSelf.git -
vibecosystem
SkillsProfile-based coding runtime for Claude Code and Codex. Lean core; opt-in quality, context, memory, orchestration and dashboard.
git clone https://github.com/vibeeval/vibecosystem.git -
lore-plugin
SkillsStop explaining your project to the AI every morning. With your approval, Lore turns lessons into project criteria the AI can use next time. Provider-neutral and local-first.
git clone https://github.com/andresanemic/lore-plugin.git -
Selvedge
MCP serversPersistent decision memory for AI agents: rationale, rejected approaches, and entity history.
selvedge@0.3.18 -
superior-skills
PromptsBuild smarter. Work superior. An opinionated rule set for AI coding agents to create original interfaces, compelling content, and production-ready code.
git clone https://github.com/KodekaTeam/superior-skills.git -
Glyd
Datasets & benchmarksLossless AI compression: 33% less GPU memory, bit for bit.
git clone https://github.com/surya-koritala/Glyd.git -
remem
MCP serversLocal-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
@remem-ai/remem@0.6.104 -
Colour Memory
MCP serversColour meaning, history and evidence for AI: 45,000+ source-graded colour records and 91 tools.
-
cognos-session-memory
MCP serversCognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
cognos-session-memory-mcp@0.1.0 -
Remember Me – Bible Memory
MCP serversMemorize Bible verses with spaced repetition: add verses, get quizzed, follow a daily reading plan.
-
Achromat Machine Operational Memory
MCP serversRecall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
@achromat-ai/mcp-server@0.1.4 -
BRICO feature memory
MCP serversFind features you built in other projects, see how they fit this one, and reuse them.
bricowerx@0.2.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.