Skip to main content
W&B HiveMind is a shared dashboard for AI coding sessions. A lightweight daemon runs on each developer’s machine, watches for coding agent activity, and sends session transcripts to hivemind.wandb.tools. Coding agents like Claude Code, Codex, Copilot, Cursor, Gemini, OpenCode, and Pi all write transcripts to the local filesystem as they work. The HiveMind daemon wakes up every 30 seconds, checks for new activity, and uploads anything it finds. There’s nothing to configure per agent. If the agent writes transcripts, HiveMind picks them up.

Get started

brew install wandb/tap/hivemind
hivemind start
The daemon starts in the background and authenticates via GitHub. That’s it.
Once the daemon is running, open any supported coding agent and start working. Within 30 seconds your session appears on the dashboard. You can watch sessions in real time, review past conversations, and dig into individual tool calls.

Explore the docs

Features

Tour the dashboard, session detail views, and the GitHub and Slack integrations.

Permissions & privacy

Control who can see your sessions, configure visibility, and set up SSO.

CLI reference

Manage the daemon, search sessions, and configure HiveMind from the command line.

Bots & service accounts

Push sessions from CI, cloud agents, and headless environments with token or OIDC auth.

Deploy with MDM

Roll HiveMind out across a fleet with JAMF, Intune, and other MDM tools.

Supported agents

HiveMind picks up transcripts from the coding agents you already use, with no per-agent setup.
AgentTranscript source
Claude Code~/.claude/projects/ JSONL files
Codex~/.codex/ session logs
Copilot CLI~/.copilot/session-state/ event logs
CursorSQLite databases in Cursor’s app data
Gemini CLI~/.gemini/ session history
OpenCode~/.opencode/ session files
Pi~/.pi/agent/sessions/ JSONL files

The HiveMind agent

HiveMind also installs a coding agent skill. Type @hivemind inside a Claude Code session to ask questions about past coding sessions: what you worked on last week, how a bug was fixed, or where a particular change was made. It searches across your team’s session history and pulls the answer into your current conversation.