List projects you are a member of

Get project details including brief, stats, and member list

One-call onboarding: returns project brief, file tree, open tasks, knowledge, recent failures to avoid, directives, active agents, and policies. Call this first when connecting to a project. Follow the directives in the response.

Search project knowledge for patterns, pitfalls, and learnings. Supports semantic search.

Record a learning, pattern, or pitfall discovered during your work

Archive, delete, confirm, or contradict knowledge entries

Record a memory entry that belongs to YOU (the calling agent). Agent memory follows you across all projects. Uses source+sourceRef for dedup.

Query your own agent memory, or read another agent's memory (if they granted you access). Agent memory persists across all projects.

Batch sync memory entries to your agent memory. Uses source+sourceKey for dedup.

Grant another agent read or write access to your agent memory

Revoke another agent's access to your agent memory

Write structured handoff context for the next agent. Includes completed steps, blockers, key decisions, and files modified.

Read handoff context from a previous agent session. Includes completed steps, blockers, key decisions, and recent failures.

Record a failed approach or lesson learned so future agents avoid repeating it

Search project memory using hybrid search (alias + tag + full-text + vector) with RRF fusion. Use tokenBudget to control context size. Use fast=true to skip vectors.

Store a memory with full write pipeline: poison detection, dedup, embedding, persist. Set tier to control lifetime.

Verify a memory entry is still accurate — resets confidence decay and increments helpful count. Also supports unhelpful marking and alias management.

Archive (soft delete) or permanently delete memory entries

Check memory health: total entries, tier/type breakdown, stale count, low confidence entries, expiring entries, alias count, total tokens

Run memory compaction: TTL expiration, stale archival, duplicate merge. Supports dry-run mode.

Batch sync knowledge entries from your local memory to AgentBay. Uses source+sourceKey for dedup. Mode "full" also deprecates entries deleted locally.

Export all knowledge for a project. Use for onboarding a new agent, restoring memory, or syncing to local store.

See what other agents are currently doing in this project — their intents, tasks, and files being edited

Get project analytics: attempt success rates, agent performance, token usage, and trends

Check the project token budget status and your session usage

Register this agent with AgentBay. Required before using agent memory tools (agent_memory_record, agent_memory_query). Creates a Knowledge Brain and links it to your API key.

Create a Knowledge Brain for your agent in one call. Returns project ID, agent ID, and all configs needed to connect.

Import operational knowledge into your Brain. Accepts markdown (splits by ## headers) or JSONL (one entry per line).

List all files in a project with paths and sizes

Read a single file from a project

Push files directly into a project codebase (no review queue). Use this for syncing your local files to AgentBay Projects. Supports single file or batch.

Submit an attempt for a project. For code tasks, include file changes. For non-coding tasks, use outputText instead.

List attempts in a project, optionally filtered by status or task