How Amoeba warns when AI coding work overlaps
A practical guide to overlap warnings, advisory file locks, team coordination choices, and the cases where agents can continue without a warning.
Multiplayer coding with AI agents: one shared session for the team
What a shared agent session is, how live context and approvals work, and why it helps teams coordinate Claude Code and Codex.
Use Claude Code or Codex in one shared AI IDE
How teammates connect supported local agent CLIs, share coordination context in Amoeba, and recover when a provider or coordination is unavailable.
Local AI coding with a shared Brain and Git sync
How local provider CLIs, hosted coordination data, encrypted transcript chunks, and Git shadow refs work together in Amoeba.
Approval gates: keeping AI agent changes off your branches until a human signs off
Roles, per-repository permissions and an approval step before any agent push. How enterprise teams run agents without giving up control.
Shared project memory: giving every AI agent the same context
Decisions, conventions and context pinned to files in your repo, readable by every agent, and flagged when the code moves.
Parallel subagents that report back as one result
How one agent splits a task into local subagents, separates their Git changes, and returns a candidate for review.
Install Amoeba and open a shared workspace
A first-run guide using Welcome and Setup, GitHub sign-in, Claude Code or Codex detection, an existing workspace connection, and team invitations.
How Amoeba separates parallel agent changes with Git worktrees
What Git worktrees separate, what local agent processes can still reach, and what to review before integrating parallel AI coding work.
Hit your AI usage limit mid-task? Hand the agent to a teammate
When a provider limit is reached, Amoeba offers to pass the live task, with its prompts and diff, to someone with capacity.