Neurohive
This wraps neuromcp with a shared knowledge layer for multi-agent teams. Every memory stored by any agent gets attributed and becomes searchable by the whole team, annotated with who discovered it and when. You get three core tools: hivemind_status for a team dashboard showing active agents and knowledge categories, hivemind_expertise to track which agent knows what topics, and hivemind_conflicts to flag contradictions when two agents store incompatible facts. New agents pull top knowledge on startup via the priming resource. Integrates with Paperclip to auto-detect company namespaces and agent identities. Reach for this when you're running multiple AI agents on the same project and need them to stop rediscovering the same facts in isolation.
- GitHub stars
- 1
- tools
- 16
- transport
- STDIO
- last updated
- Apr 4, 2026
Tools
16 toolsPublic tool metadata for what this MCP can expose to an agent.
store_memoryStore memory with hive annotations
Store memory with hive annotations
No parameter schema in public metadata yet.
search_memoryHybrid search with cross-agent attribution
Hybrid search with cross-agent attribution
No parameter schema in public metadata yet.
recall_memoryRecall by ID, namespace, category, or tags
Recall by ID, namespace, category, or tags
No parameter schema in public metadata yet.
forget_memorySoft-delete memories by filter
Soft-delete memories by filter
No parameter schema in public metadata yet.
consolidateMerge duplicates, decay stale, prune low-value
Merge duplicates, decay stale, prune low-value
No parameter schema in public metadata yet.
memory_statsCount, category, and trust-level statistics
Count, category, and trust-level statistics
No parameter schema in public metadata yet.
export_memoriesExport as JSONL or JSON
Export as JSONL or JSON
No parameter schema in public metadata yet.
import_memoriesImport with deduplication
Import with deduplication
No parameter schema in public metadata yet.
backfill_embeddingsRecompute missing embeddings
Recompute missing embeddings
No parameter schema in public metadata yet.
create_entityCreate/update knowledge graph entity
Create/update knowledge graph entity
No parameter schema in public metadata yet.
create_relationLink entities in knowledge graph
Link entities in knowledge graph
No parameter schema in public metadata yet.
query_graphTraverse knowledge graph
Traverse knowledge graph
No parameter schema in public metadata yet.
search_claimsSearch atomic extracted claims
Search atomic extracted claims
No parameter schema in public metadata yet.
hivemind_statusTeam dashboard: agents, categories, conflicts, activity
Team dashboard: agents, categories, conflicts, activity
No parameter schema in public metadata yet.
hivemind_expertiseQuery who knows what; get agent expertise profiles
Query who knows what; get agent expertise profiles
No parameter schema in public metadata yet.
hivemind_conflictsList/resolve inter-agent contradictions
List/resolve inter-agent contradictions
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
neurohive
Multi-agent memory intelligence — shared knowledge, expertise tracking, and conflict detection for AI agent teams.
Why
AI agents in teams forget everything and don't share knowledge. Multiple agents working on the same project re-discover the same facts, contradict each other, and have no collective memory. One agent learns the API timeout is 30 seconds; another assumes 60. Both conclusions sit in separate sessions, never compared.
neurohive wraps neuromcp with a shared intelligence layer. Every memory stored by any agent becomes visible to the team. Searches come back annotated with who discovered what and when. New agents onboard with the team's existing knowledge already loaded. Contradictions get flagged before they cause incidents.
Before & After
Details
- Repository
- github.com/adelelo13/neurohive
- Category
- AI & LLM Tools
- Package
neurohive- Transport
- STDIO
- Registry
- MCP registry, active
More from adelelo13
Related AI & LLM Tools MCP servers
View all
Safebot Chatalexkirienko/safebot-chatEnd-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.1stars
Boardcheckecholonius/boardcheckFlags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection1stars
AI Skill Storegarasegae/aiskillstoreAgent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.1stars
Toolroutegrossiweb/toolrouteRoute AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.1stars
Wisepanelikoskela/wisepanel-mcpMulti-agent deliberation across Claude, Gemini, and Perplexity. Stream and publish.1stars