Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
MALN — Multi-Agent Learning Network
MCP serversVerified trust ledger for agents: claims graded by a real oracle, never self-reported.
-
AgentRecall-X
MCP serversCorrection-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
git clone https://github.com/Goldentrii/AgentRecall-X.git -
altk-evolve
MCP serversSelf improving agents through iterations
git clone https://github.com/AgentToolkit/altk-evolve.git -
skillmem
MCP serversSkill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.
skillmem@0.13.0 -
BanditDB
MCP serversPersistent decision memory for agents — learns which action works in which context
banditdb-python@0.3.1 -
SuperMemory
MCP serversMCP-first agent learning: capture failures, validate lessons, retrieve context, improve.
supermemory-agent@0.2.5 -
brainbox
MCP serversHebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.
brainbox-hebbian@0.1.6 -
Contextloop
MCP serversTeam metric definitions for data agents. Learns from corrections, tracks SQL answer accuracy.
-
Brevet
MCP serversChange control for what AI agents learn: humans promote, releases are signed, rules can be recalled
brevet@0.4.0 -
Recall
MCP serversLong-term memory for AI agents: learns what is true about each person and answers with sources.
-
Hivemind
MCP serversShared long-term memory for a team's AI agents. What one agent learns, the others can find.
ghcr.io/monochrome-muncher/hivemind:v2.27.2 -
Context Vault
MCP serversHosted memory for AI agents: save what your agent learns and recall it in the next session.
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.