Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
FastrMemory
MCP serversLocal-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid retrieval.
fastrmemory@0.9.3 -
GraphyLoop
MCP serversWorkflow planner, wave dispatcher, persistent swarm memory, and deploy preflight for AI agents.
graphyloop@0.6.5 -
AgentContinuity
MCP serversPrivate memory, scratchpads, context export/restore and task handoff for AI agents.
-
decisiontrail
MCP serversLocal decision memory for coding agents: record decisions with limits, search precedents, supersede.
@reneturcios/decisiontrail@0.1.0 -
dmt-receipts
MCP serversPrepare and verify TAP/Ordinals payloads for AI agent memories on Bitcoin.
https://github.com/Colchora/dmt-receipts/releases/download/v0.2.0/dmt-receipts-0.2.0.mcpb -
dmt-receipts
MCP serversStamp and verify Bitcoin-anchored OpenTimestamps memory receipts for AI agents.
https://github.com/many77146-bot/dmt-receipts/releases/download/v0.1.0/dmt-receipts-0.1.0.mcpb -
Woolly
MCP serversOne local memory for all your AI apps. Private, plain files, open source.
https://github.com/rjcuff/woolly/releases/download/v0.14.1/woolly.mcpb -
RefLib
MCP serversAssistants search and read RefLib corpora by section, not from model memory.
-
AxioDB
MCP serversEmbedded NoSQL Database for TypeScript & AI Agents. Zero-native document database with ACID transactions & in-memory cache — verified on Node.js & Bun.
git clone https://github.com/nexoral/AxioDB.git -
graphersal
MCP serversIn-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.
git clone https://github.com/graphersal/graphersal.git -
coddy-agent
Agents & frameworksGeneral-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gateway, cron scheduler, swarm relay, remote mode. Rules, skills, subagents, hooks, MCP, background tasks, long-term memory, context compaction. Any OpenAI-compatible provider, distroless-ready.
git clone https://github.com/coddy-project/coddy-agent.git -
neurolink
Tools & appsThe pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide (via TypeSafe Jev). MCP-native, voice (TTS/STT/realtime), RAG, memory, file processors. Powers Tara, Yama and Clairvoyance at Juspay.
git clone https://github.com/juspay/neurolink.git -
auditor-skill
SkillsClaude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20 checklists, and 131 real-world attack vectors.
git clone https://github.com/solanabr/auditor-skill.git -
Daystruct
MCP serversDiscover reusable source, data and memory capabilities; inspect release evidence and compatibility.
-
khive
MCP serversPersistent memory, knowledge graph, task management and more for AI agents via MCP.
-
MAGNEMO
MCP serversPersistent Memory for AI Agents, in plain local files. No network calls of its own.
magnemo-mcp@0.6.11 -
Megastructure Arc
MCP serversLocal hub your coding agents sign into: rooms, tasks, decisions, artifacts, memory. Desktop app.
-
MemoryRouter
MCP serversPersistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
-
mitosis
MCP serversMitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
-
OneDroid Engram
MCP serversVersioned agent memory in your own Postgres: portable context, permissioned, audit trail.
-
Vocci
MCP serversRead-only MCP access to authorized Vocci sessions, notes, files, and memory search.
-
mcp
MCP serversYour memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
-
Jade Note
MCP serversMCP-native notes and memory for ChatGPT, Claude, and other AI tools.
-
A2A Orbit
MCP serversShared memory for AI agents: prior work, failures, checkpoints, handoffs, and artifacts.
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.