On_Board

swisspra/On_Board

★ 0 stars Python 🤖 AI/LLM Updated today

Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "on_board": {
      "command": "uvx",
      "args": [
        "on-board"
      ]
    }
  }
}

Or install with pip: pip install on-board

README Excerpt

One project, one shared memory, every agent platform. On Board stores project context in `.agent-mem/` so Claude, Cursor, Codex, Claude Code, AntiGravity, and other MCP clients can continue work without losing decisions, warnings, tickets, or handoffs. - `memory_onboard` is now the preferred first call for every agent session.

Tools (17)

AGENT_MEM_CONTEXT_DIRSAGENT_MEM_HOT_HOURSAGENT_MEM_IDLE_KIA_MINAGENT_MEM_MAX_HOTAGENT_MEM_VECTOR_BACKENDAGENT_PROJECT_DIRbriefdeepmemory_cancel_ticketmemory_claim_ticketmemory_create_ticketmemory_initmemory_list_ticketsmemory_review_ticketmemory_submit_ticketmemory_terminate_ticketnormal

Topics

a2aagent-memoryantigravityclaudecodexcursormcpmcp-servermulti-agent

On_Board

Quick Install

README Excerpt

Tools (17)

Topics

Related AI/LLM Servers