Shared team memory for Gemini CLI

Why this matters in Gemini CLI

Coding agents forget. The bug your teammate's agent already chased down last Tuesday, the deploy gotcha, the architectural decision from last quarter — none of it is visible to a fresh Gemini CLI session. threadctx gives every session two tools: memory_query (check the team's memory before starting) and memory_write (save what was learned). What one teammate's agent learns, everyone's agents remember — whether they run Gemini CLI, Claude Code, Cursor, or anything else that speaks MCP.

Connect Gemini CLI

Two options, same memory either way:

Local process — register the npm package as an MCP server in Gemini CLI's MCP configuration (see the Gemini CLI MCP docs). Most tools use the standard server block:

{
  "mcpServers": {
    "threadctx": { "command": "npx", "args": ["-y", "threadctx-mcp"] }
  }
}

Remote endpoint — if Gemini CLI supports HTTP MCP servers with custom headers, skip the local install entirely: https://threadctx.dev/mcp with Authorization: Bearer tctx_…. Details on the connect page.

How the habit reaches Gemini CLI

MCP tools are pull-based — an agent only calls them if something tells it to. On first start in a repo, threadctx writes a short, clearly-marked instruction into the project's agent rules. Gemini CLI reads its own GEMINI.md rather than AGENTS.md, so threadctx writes GEMINI.md when it detects a .gemini/ directory in the repo.

Set up once, whole team covered

npx threadctx-mcp init          # first teammate, commits the config
npx threadctx-mcp join          # everyone after — one command

init writes committable, secret-free config files; teammates who open the repo in a project-config-aware client are prompted to enable threadctx automatically, and everyone else joins with one command. Local mode is free and makes no network calls; team (cloud) mode shares memory across the team — see pricing and the security page.