# StremAI Full LLM Inventory

StremAI is the one brain for all your coding agents: persistent memory, collaboration, and governance for coding agents.

Generated from the repository surface inventory on 2026-05-17. Use public/llms.txt for the short version.

## Agent Install Docs

- Fresh install: https://stremai.com/install-help-for-agents
- Repeated sessions: https://stremai.com/llms.txt
- Hosted MCP: https://stremai.com/api/mcp
- OpenAPI: https://stremai.com/api/openapi

## One-Paste Agent Install

```text
Install StremAI in this project as the one brain for all your coding agents.
Try `pip install stremai` and `npm install @tmjumper/stremai`; if MCP is available, connect https://stremai.com/api/mcp with OAuth/browser sign-in. If the client cannot complete OAuth, create an API key from https://stremai.com/dashboard/connect and use Authorization: Bearer $AGENTBAY_API_KEY as the fallback. Verify by storing one PATTERN memory, then recall it before editing code.
```

## Canonical Answer Blocks

### What is StremAI?

StremAI is a shared memory layer for AI coding agents. Connected agents — in tools like Claude Code, Codex, Cursor, and other MCP-compatible clients — can store what they learn while working, and other connected agents can recall it later, across sessions, machines, and tools. Memory is user-controlled: entries are human-readable, attributed to the agent that stored them, and can be exported, archived, or erased at any time. Setup is one command over MCP, free to start with no credit card. Verified with Claude Code and Claude Desktop; other MCP clients are supported or in active verification. Start at stremai.com/getting-started.

Try a public recall at https://stremai.com/playground. For a portable recall/store/verify/handoff routine, see https://stremai.com/docs/agent-memory-protocol.

### How is StremAI different from CLAUDE.md and AGENTS.md?

They're complementary, and most developers should use both. CLAUDE.md and AGENTS.md hold instructions you write — conventions, build commands, rules — checked into the repo and read at session start. StremAI holds something different: memory agents accumulate while working — decisions, pitfalls, project context — stored as attributed entries and recalled selectively, so a session gets the few relevant memories rather than one ever-growing file. Keep your instruction files; StremAI does not replace them. It adds the learned layer they were never designed to carry.

### How does StremAI work with MCP?

StremAI is an MCP server. Any MCP-compatible client can connect to it — hosted over HTTP at stremai.com/api/mcp with OAuth sign-in, or via a local stdio package — and gains memory tools: store, recall, verify, and session handoff. When an agent calls recall, StremAI searches stored memories several ways at once (aliases, tags, keywords, semantic similarity) and returns a small ranked set of relevant entries rather than a full dump. Because MCP is an open standard, one memory layer can serve several different tools. Verified with Claude Code and Claude Desktop; other MCP clients are supported or in active verification.

### Does StremAI train on user data?

No. Stored memories are used to serve your own recalls — nothing else. StremAI stores the short entries agents explicitly save, not your codebase; there is no repository ingestion or ambient capture. Memory content is encrypted in transit and at the field level at rest, and search embeddings are generated via a subprocessor named in the privacy policy solely so your own recall works. There is no cross-customer access, and no model training on user data. If model-adaptation features are ever offered, they would be opt-in and permissioned — today they do not exist. Details: stremai.com/security.

## API Endpoints (231)

- /api/admin/activation/cohort-users
- /api/admin/activation/cohorts
- /api/admin/activation/funnel
- /api/admin/activation/nudge
- /api/admin/cancellation-insights
- /api/admin/email-digest
- /api/admin/error-log
- /api/admin/impersonation
- /api/admin/incidents
- /api/admin/inngest-health
- /api/admin/metrics
- /api/admin/operational-flags
- /api/admin/slack-webhook
- /api/admin/stats
- /api/admin/users
- /api/auth/[...nextauth]
- /api/cron/daily
- /api/cron/exports
- /api/cron/reset-spending
- /api/cron/retention
- /api/cron/stats-digest
- /api/git/[...path]
- /api/health
- /api/health/deep
- /api/health/ready
- /api/inngest
- /api/internal/admin/users
- /api/internal/api-keys
- /api/internal/api-keys/[id]/reveal
- /api/internal/auth/session
- /api/internal/backfill-encryption
- /api/internal/credits/checkout
- /api/internal/feedback
- /api/internal/invite-codes
- /api/internal/invite-codes/validate
- /api/internal/memory
- /api/internal/memory/graph
- /api/internal/memory/search
- /api/internal/onboarding/install-confirm
- /api/internal/onboarding/progress
- /api/internal/onboarding/seed-memories
- /api/internal/settings
- /api/internal/setup-tokens
- /api/internal/setup-tokens/quick
- /api/internal/setup/status
- /api/internal/usage
- /api/mcp
- /api/openapi
- /api/playground
- /api/shared-brains
- /api/shared-brains/[id]
- /api/v1/account/delete-request
- /api/v1/account/delete-request/cancel
- /api/v1/account/email/change-request
- /api/v1/account/email/undo
- /api/v1/account/email/verify
- /api/v1/account/export
- /api/v1/account/sessions
- /api/v1/account/sessions/[id]
- /api/v1/admin/stats
- /api/v1/agents
- /api/v1/agents/[agentId]
- /api/v1/agents/[agentId]/api-key
- /api/v1/agents/[agentId]/memory
- /api/v1/agents/[agentId]/memory/export
- /api/v1/agents/[agentId]/memory/permissions
- /api/v1/agents/[agentId]/memory/sync
- /api/v1/agents/[agentId]/recall-events
- /api/v1/agents/[agentId]/recall-events/export
- /api/v1/agents/teams
- /api/v1/auth/agent-sessions
- /api/v1/auth/agent-sessions/[token]
- /api/v1/auth/agent-sessions/[token]/complete
- /api/v1/auth/connect/[token]
- /api/v1/auth/forgot-password
- /api/v1/auth/login
- /api/v1/auth/magic-link/consume
- /api/v1/auth/magic-link/request
- /api/v1/auth/register
- /api/v1/auth/resend-verification
- /api/v1/auth/reset-password
- /api/v1/auth/setup
- /api/v1/auth/verify-email
- /api/v1/auth/verify-email/code
- /api/v1/billing/cancel
- /api/v1/billing/cancel-trial
- /api/v1/billing/checkout
- /api/v1/billing/portal
- /api/v1/billing/portal-session
- /api/v1/billing/reactivate
- /api/v1/billing/trial
- /api/v1/brain/import
- /api/v1/brain/setup
- /api/v1/brain/test
- /api/v1/credits/purchase
- /api/v1/health
- /api/v1/internal/conversion-intent
- /api/v1/keys/rotate
- /api/v1/me
- /api/v1/memory/[id]/permissions
- /api/v1/memory/list
- /api/v1/memory/permissions/bulk
- /api/v1/memory/recent
- /api/v1/memory/search
- /api/v1/memory/search-across
- /api/v1/memory/sharing-rules
- /api/v1/onboarding
- /api/v1/project-templates
- /api/v1/projects
- /api/v1/projects/[id]
- /api/v1/projects/[id]/activity
- /api/v1/projects/[id]/activity/handoff
- /api/v1/projects/[id]/activity/heartbeat
- /api/v1/projects/[id]/activity/resume
- /api/v1/projects/[id]/activity/stream
- /api/v1/projects/[id]/analytics
- /api/v1/projects/[id]/archive
- /api/v1/projects/[id]/attempts
- /api/v1/projects/[id]/attempts/[attemptId]
- /api/v1/projects/[id]/attempts/[attemptId]/merge
- /api/v1/projects/[id]/attempts/[attemptId]/reject
- /api/v1/projects/[id]/attempts/[attemptId]/reviews
- /api/v1/projects/[id]/audit-logs
- /api/v1/projects/[id]/budget
- /api/v1/projects/[id]/clone
- /api/v1/projects/[id]/conflicts/files
- /api/v1/projects/[id]/dashboard-hero
- /api/v1/projects/[id]/destroy
- /api/v1/projects/[id]/docs
- /api/v1/projects/[id]/erasure
- /api/v1/projects/[id]/files
- /api/v1/projects/[id]/files/[...path]
- /api/v1/projects/[id]/files/history
- /api/v1/projects/[id]/governance
- /api/v1/projects/[id]/graph
- /api/v1/projects/[id]/handoffs
- /api/v1/projects/[id]/handoffs/[handoffId]
- /api/v1/projects/[id]/handoffs/[handoffId]/resume
- /api/v1/projects/[id]/invitations
- /api/v1/projects/[id]/invitations/[invitationId]
- /api/v1/projects/[id]/join
- /api/v1/projects/[id]/knowledge
- /api/v1/projects/[id]/knowledge/export
- /api/v1/projects/[id]/knowledge/sync
- /api/v1/projects/[id]/manifest
- /api/v1/projects/[id]/manifest/roster
- /api/v1/projects/[id]/members
- /api/v1/projects/[id]/members/[userId]
- /api/v1/projects/[id]/members/[userId]/config
- /api/v1/projects/[id]/members/[userId]/config/rollback
- /api/v1/projects/[id]/memory
- /api/v1/projects/[id]/memory/compact
- /api/v1/projects/[id]/memory/context-pack
- /api/v1/projects/[id]/memory/dream
- /api/v1/projects/[id]/memory/events
- /api/v1/projects/[id]/memory/events/[eventId]
- /api/v1/projects/[id]/memory/events/[eventId]/feedback
- /api/v1/projects/[id]/memory/import
- /api/v1/projects/[id]/memory/quality
- /api/v1/projects/[id]/memory/stale
- /api/v1/projects/[id]/memory/store-batch
- /api/v1/projects/[id]/onboard
- /api/v1/projects/[id]/policies
- /api/v1/projects/[id]/push
- /api/v1/projects/[id]/reviews
- /api/v1/projects/[id]/routing
- /api/v1/projects/[id]/search
- /api/v1/projects/[id]/souls
- /api/v1/projects/[id]/souls/[agentId]
- /api/v1/projects/[id]/specs
- /api/v1/projects/[id]/star
- /api/v1/projects/[id]/symbols
- /api/v1/projects/[id]/tasks
- /api/v1/projects/[id]/tasks/[taskId]
- /api/v1/projects/[id]/tasks/[taskId]/claim
- /api/v1/projects/[id]/tasks/[taskId]/decompose
- /api/v1/projects/[id]/tasks/[taskId]/lock
- /api/v1/projects/[id]/templates
- /api/v1/projects/[id]/unarchive
- /api/v1/projects/[id]/verification
- /api/v1/projects/import/github
- /api/v1/sdk/entitlement
- /api/v1/sdk/usage
- /api/v1/shared-brains
- /api/v1/shared-brains/[id]
- /api/v1/shared-brains/[id]/toggle-public
- /api/v1/tasks/[taskId]/resolve
- /api/v1/teams
- /api/v1/teams/[teamId]
- /api/v1/teams/[teamId]/activity
- /api/v1/teams/[teamId]/analytics
- /api/v1/teams/[teamId]/audit-log
- /api/v1/teams/[teamId]/billing
- /api/v1/teams/[teamId]/dream
- /api/v1/teams/[teamId]/events
- /api/v1/teams/[teamId]/invitations
- /api/v1/teams/[teamId]/invitations/[id]
- /api/v1/teams/[teamId]/invitations/[id]/accept
- /api/v1/teams/[teamId]/invitations/[id]/reject
- /api/v1/teams/[teamId]/leave
- /api/v1/teams/[teamId]/members
- /api/v1/teams/[teamId]/messages
- /api/v1/teams/[teamId]/onboard
- /api/v1/teams/[teamId]/policy
- /api/v1/teams/[teamId]/recall
- /api/v1/teams/[teamId]/recall-events
- /api/v1/teams/[teamId]/recall-events/export
- /api/v1/teams/[teamId]/shared-memories
- /api/v1/teams/[teamId]/usage
- /api/v1/telemetry/install
- /api/v1/timemachine/[id]
- /api/v1/timemachine/diff
- /api/v1/timemachine/list
- /api/v1/timemachine/restore
- /api/v1/usage/current
- /api/v1/waitlist
- /api/webhooks/stripe

## MCP Tools (137)

- agentbay_activity_query
- agentbay_agent_cleanup
- agentbay_agent_delete
- agentbay_agent_list
- agentbay_agent_memory_grant
- agentbay_agent_memory_query
- agentbay_agent_memory_record
- agentbay_agent_memory_revoke
- agentbay_agent_memory_sync
- agentbay_agent_register
- agentbay_agent_set_webhook
- agentbay_agent_update
- agentbay_agent_wake
- agentbay_agent_whoami
- agentbay_analytics
- agentbay_attempt_list
- agentbay_attempt_review_create
- agentbay_attempt_reviews
- agentbay_attempt_submit
- agentbay_audit_logs
- agentbay_brain_compare
- agentbay_brain_import
- agentbay_brain_restore
- agentbay_brain_setup
- agentbay_brain_snapshot
- agentbay_brain_snapshots
- agentbay_brain_test
- agentbay_budget_check
- agentbay_bulk_recall
- agentbay_bulk_store
- agentbay_capabilities
- agentbay_config_history
- agentbay_config_update
- agentbay_conflict_check
- agentbay_erasure_list
- agentbay_governance_status
- agentbay_handoff_create
- agentbay_handoff_list
- agentbay_handoff_resume
- agentbay_intent_register
- agentbay_knowledge_export
- agentbay_knowledge_manage
- agentbay_knowledge_query
- agentbay_knowledge_record
- agentbay_knowledge_sync
- agentbay_manifest_get
- agentbay_manifest_update
- agentbay_memory_compact
- agentbay_memory_diff
- agentbay_memory_dream
- agentbay_memory_event_get
- agentbay_memory_events
- agentbay_memory_forget
- agentbay_memory_graph
- agentbay_memory_graph_at
- agentbay_memory_health
- agentbay_memory_history
- agentbay_memory_inject
- agentbay_memory_learn
- agentbay_memory_link
- agentbay_memory_link_temporal
- agentbay_memory_prefetch
- agentbay_memory_quality
- agentbay_memory_recall
- agentbay_memory_recommend
- agentbay_memory_related
- agentbay_memory_relation_history
- agentbay_memory_self_heal
- agentbay_memory_self_refine
- agentbay_memory_stale
- agentbay_memory_store
- agentbay_memory_strategy_insights
- agentbay_memory_timeline
- agentbay_memory_transfer
- agentbay_memory_transfer_suggest
- agentbay_memory_uncertain
- agentbay_memory_verify
- agentbay_message_read
- agentbay_message_send
- agentbay_message_unread
- agentbay_pool_assign
- agentbay_pool_broadcast
- agentbay_pool_create
- agentbay_pool_status
- agentbay_project_create
- agentbay_project_dead_code
- agentbay_project_docs
- agentbay_project_file_history
- agentbay_project_files
- agentbay_project_get
- agentbay_project_graph_query
- agentbay_project_impact_analysis
- agentbay_project_ingest
- agentbay_project_ingest_estimate
- agentbay_project_join
- agentbay_project_list
- agentbay_project_onboard
- agentbay_project_push_files
- agentbay_project_read_file
- agentbay_project_routing
- agentbay_project_search
- agentbay_project_specs
- agentbay_project_structure
- agentbay_raw
- agentbay_record_failure
- agentbay_session_handoff
- agentbay_session_resume
- agentbay_signup
- agentbay_soul_get
- agentbay_soul_team
- agentbay_soul_update
- agentbay_symbol_link
- agentbay_symbol_query
- agentbay_task_claim
- agentbay_task_create
- agentbay_task_decompose
- agentbay_task_get
- agentbay_task_list
- agentbay_task_lock
- agentbay_task_unlock
- agentbay_task_update
- agentbay_team_dream
- agentbay_team_invitations
- agentbay_team_invite
- agentbay_team_onboard
- agentbay_team_recall
- agentbay_team_set_policy
- agentbay_trigger_create
- agentbay_trigger_delete
- agentbay_trigger_list
- agentbay_whoami

## Doc Pages (19)

- /docs
- /docs/agent-memory-protocol
- /docs/claude-code
- /docs/claude-code-memory
- /docs/codex
- /docs/codex-memory
- /docs/cursor
- /docs/cursor-memory
- /docs/from-mem0
- /docs/hermes
- /docs/how-memory-works
- /docs/integrations
- /docs/mcp-memory
- /docs/oauth
- /docs/openclaw
- /docs/python-sdk
- /docs/typescript-sdk
- /docs/what-agents-remember
- /docs/windsurf

## Key Public Pages

- /benchmarks
- /benchmarks/locomo
- /compare/claude-md-vs-stremai
- /compare/cursor-rules-vs-stremai
- /compare/copilot-memory-vs-stremai
- /compare/mem0-vs-stremai
- /compare/zep-vs-stremai
- /compare/enterprise-knowledge-tools-vs-stremai
- /getting-started
- /install-help-for-agents
- /pricing

## Packages (6)

- stremai@1.9.3 (Python): `pip install stremai`
- @tmjumper/stremai@1.1.9 (npm): `npm install @tmjumper/stremai`
- aiagentsbay-mcp@1.2.5 (npm compatibility package): `npx aiagentsbay-mcp`
- agentbay@1.9.2 (Python compatibility package)
- agentbay@1.1.8 (npm compatibility package)
- agentbay-openclaw@0.5.0