Collaborative AI memory for engineering teams - share context across Claude Code, Cursor, and teammates
View on GitHub ↗Collaborative AI memory for engineering teams.
When you and your teammates use Claude Code or Cursor on the same Jira ticket or GitHub issue, every session re-crunches the same context from scratch. HiveShare fixes that: anything one person's AI agent processes gets stored as searchable memory in a shared hiveshare, so everyone else's agent reuses it immediately — no re-reading, no re-summarising.
- Isolated hiveshares — one per project, story, or sprint; fully separate hive stores - Invite by email — token-based, no SMTP required; teammates get their own API key on accept - Live sync — hiveshare stream shows new entries from any teammate in real time (SSE; one Redis sub per hiveshare) - Semantic search — OpenAI or Ollama embeddings (async on write, HNSW index); falls back to PostgreSQL full-text if not configured - MCP integration — Claude Code and Cursor can search and save memory automatically without you doing anything - Metrics — reuse rate, top contributors, source coverage, 7-day activity - Unique source refs — one hive per sourceref per hiveshare; duplicates are auto-suffixed (PROJ-42-2) so saves never conflict - Hive deletion — write-access members can delete any hive; Redis view counters are cleaned up and a hivedeleted event is broadcast over SSE - Version history — every content change is recorded; roll back a hive or undelete after removal - Snapshots — capture a hiveshare point-in-time and restore into a new hiveshare; copy hives between spaces - Hardened API — hashed API keys, rate limits, body size cap, request timeouts, GET /health
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/KB-perByte--hiveshare.html)
MCP server that lets your AI assistant read and write Figma in real time — no API token, no rate limits. Works with Claude, Cursor, Copilot, Codex and any MCP client.
sainitish1609/mcp-guard🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
Kerneta/daidocsOpen plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP serve
SysikNagibator/AiPCGive the agent "this" and he gets a real PC.
junxchan54-maker/mcd-cn-assistant🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill s
Koragraph/KoragraphMCPThe memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.