# Meerkat

> A library-first Rust platform for agents, durable sessions, and multi-agent orchestration

- [Introduction](https://docs.rkat.ai/introduction.md): Meerkat is a library-first Rust platform for building, hosting, and operating agents.
- [Quickstart](https://docs.rkat.ai/quickstart.md): Install Meerkat, configure one provider, and run a first realm-backed session.
- [Auth](https://docs.rkat.ai/guides/auth.md): Realm-scoped credential resolution: from the env-var happy path to OAuth, cloud IAM, and per-member overrides
- [Concepts Overview](https://docs.rkat.ai/concepts/overview.md): The conceptual map of Meerkat: realms, sessions, runtime capabilities, and orchestration.
- [Composability](https://docs.rkat.ai/concepts/composability.md): Why Meerkat is both a composable library and a practical product layer.
- [Realms](https://docs.rkat.ai/concepts/realms.md): The identity, isolation, storage, and durability boundary shared across Meerkat surfaces.
- [Realm Inheritance](https://docs.rkat.ai/concepts/realm-inheritance.md): How config and credentials compose through a parent chain while every durable state domain stays local.
- [Sessions](https://docs.rkat.ai/concepts/sessions.md): Realm-scoped agent lifecycle, transcript, persistence, events, and recovery.
- [Auth And Bindings](https://docs.rkat.ai/concepts/auth-and-bindings.md): How Meerkat resolves a model backend, account, and credential source without storing secrets in sessions.
- [Memory And Compaction](https://docs.rkat.ai/concepts/memory-and-compaction.md): The long-horizon conversation model: context compaction plus semantic recall.
- [Comms](https://docs.rkat.ai/concepts/comms.md): How long-lived agents exchange messages and external events in Meerkat.
- [Mobs](https://docs.rkat.ai/concepts/mobs.md): Meerkat's multi-agent model: durable teams, stable member identity, role profiles, placement, wiring, flows, and operator boundaries.
- [Scheduling](https://docs.rkat.ai/concepts/scheduling.md): Durable automated work over time: triggers, targets, occurrences, and delivery policies.
- [WorkGraph](https://docs.rkat.ai/concepts/workgraph.md): Realm-scoped durable commitments, dependencies, readiness, claims, and evidence.
- [Tools](https://docs.rkat.ai/concepts/tools.md): Trait-based tool dispatch, MCP server integration, and built-in tool categories.
- [Providers](https://docs.rkat.ai/concepts/providers.md): Model catalog, provider resolution, capability gating, parameters, and fallback.
- [Configuration](https://docs.rkat.ai/concepts/configuration.md): Realm-scoped config, generation CAS, and surface-consistent runtime settings.
- [Self-hosting models](https://docs.rkat.ai/guides/self-hosting-models.md): Register OpenAI-compatible local or private model servers, including the Gemma 4 aliases Meerkat supports.
- [Image generation](https://docs.rkat.ai/guides/image-generation.md): Generate or edit assistant-owned images through the session-scoped generate_image tool.
- [Realm Guide](https://docs.rkat.ai/guides/realms.md): Choose a realm, understand its physical root, and share or isolate state deliberately.
- [Structured output guide](https://docs.rkat.ai/guides/structured-output.md): Force agents to produce validated JSON conforming to a user-provided schema
- [Memory and compaction](https://docs.rkat.ai/guides/memory.md): Automatic context compaction and semantic memory for long-running conversations
- [Hooks guide](https://docs.rkat.ai/guides/hooks.md): Typed extension points within the agent loop for observation and guardrails
- [Skills guide](https://docs.rkat.ai/guides/skills.md): Domain-specific knowledge injection via markdown documents with YAML frontmatter
- [Scheduling Guide](https://docs.rkat.ai/guides/scheduling.md): Automate durable session and mob work with once, interval, and calendar schedules.
- [Durable Jobs and Monitors](https://docs.rkat.ai/guides/durable-jobs.md): Run detached work durably, inspect its lifecycle, subscribe to delivery, and compose jobs with Schedule and WorkGraph.
- [WorkGraph Guide](https://docs.rkat.ai/guides/workgraph.md): Use WorkGraph tools to create, link, claim, evidence, close, and observe durable work.
- [Live Channels](https://docs.rkat.ai/guides/realtime.md): Open live audio/text channels with model-gated image input using realtime-capable models and the live/* RPC surface.
- [Inter-agent communication](https://docs.rkat.ai/guides/comms.md): Built-in messaging system for coordination between multiple agent instances
- [Mobs Guide](https://docs.rkat.ai/guides/mobs.md): Build and operate Meerkat multi-agent teams: delegation, members, wiring, flows, work lanes, profiles, and mobpacks.
- [Temporary Councils Guide](https://docs.rkat.ai/guides/temporary-councils.md): Convene a bounded, short-lived council of forked participants from other mobs, merge one explicit result back, and tear it down.
- [Mobpack and Web Deployment](https://docs.rkat.ai/guides/mobpack.md): Portable multi-agent deployment with signed .mobpack artifacts and browser-target web bundles.
- [Examples gallery](https://docs.rkat.ai/examples/gallery.md): Runnable applications and focused patterns built with Meerkat, from session basics to browser war games.
- [Examples: Sessions & streaming](https://docs.rkat.ai/examples/sessions.md): Session lifecycle, multi-turn conversations, event streaming, model selection, and config management.
- [Tools & MCP](https://docs.rkat.ai/examples/tools.md): Custom tools, built-in tools, MCP server management, live MCP controls, and tool scoping.
- [Hooks examples](https://docs.rkat.ai/examples/hooks.md): Lifecycle and committed-fact hooks for reactions, audit, and guardrails.
- [Skills examples](https://docs.rkat.ai/examples/skills.md): Load, discover, inject, and inspect domain-specific knowledge packs.
- [Memory & compaction](https://docs.rkat.ai/examples/memory.md): Semantic memory indexing, context compaction, and budget controls.
- [WorkGraph Example](https://docs.rkat.ai/examples/workgraph.md): A realistic multi-step workflow using dependencies, claims, evidence, and readiness.
- [Structured output examples](https://docs.rkat.ai/examples/structured-output.md): JSON schema extraction with validation, retries, and provider compatibility.
- [Comms & external events](https://docs.rkat.ai/examples/comms.md): Keep-alive sessions, typed comms commands, peer discovery, and durable external event ingress.
- [Mobs Examples](https://docs.rkat.ai/examples/mobs.md): Create mobs, spawn members, wire peers, send work, and run flows through the current host control plane.
- [Mobpack](https://docs.rkat.ai/examples/mobpack.md): Portable multi-agent deployment with signed archives and trust policies.
- [Examples: WASM runtime](https://docs.rkat.ai/examples/wasm.md): Browser deployment with the meerkat-web-runtime embedded surface.
- [Rust SDK overview](https://docs.rkat.ai/rust/overview.md): Embed Meerkat as a Rust library: the full engine with no subprocess overhead.
- [Tools and stores](https://docs.rkat.ai/rust/tools-and-stores.md): Rust SDK reference for the tool system, session stores, and MCP integration.
- [Rust SDK advanced](https://docs.rkat.ai/rust/advanced.md): Expert-level direct agent construction, provider configuration, budgets, hooks, and runtime delivery internals.
- [Python SDK](https://docs.rkat.ai/sdks/python/overview.md): Get started with the Meerkat Python SDK: sessions, streaming, schedules, mobs, and typed runtime contracts.
- [Python SDK reference](https://docs.rkat.ai/sdks/python/reference.md): Public types and behavior for the Meerkat Python SDK.
- [TypeScript SDK](https://docs.rkat.ai/sdks/typescript/overview.md): Getting started with the Meerkat TypeScript SDK: sessions, turns, streaming events, and capabilities.
- [TypeScript SDK reference](https://docs.rkat.ai/sdks/typescript/reference.md): Types, events, error classes, and version compatibility for the @rkat/sdk TypeScript SDK.
- [CLI commands](https://docs.rkat.ai/cli/commands.md): Command reference for the task-first, Unix-native rkat CLI.
- [CLI configuration](https://docs.rkat.ai/cli/configuration.md): Realm selection, storage behavior, environment variables, MCP config, and exit codes for rkat.
- [REST API](https://docs.rkat.ai/api/rest.md): HTTP server for running and managing agent sessions over REST endpoints.
- [JSON-RPC stdio server](https://docs.rkat.ai/api/rpc.md): Stateful JSON-RPC 2.0 interface for stdio, TCP, and optional WebSocket or WebRTC live channels.
- [MCP](https://docs.rkat.ai/api/mcp.md): Use Meerkat as an MCP client to call external tools, or expose Meerkat as MCP tools for other clients.
- [API reference](https://docs.rkat.ai/reference/api-reference.md): Index of public types, traits, and error codes in Meerkat.
- [Built-in tools reference](https://docs.rkat.ai/reference/builtin-tools.md): Comprehensive reference for all built-in tools available in Meerkat, including parameters, types, and defaults.
- [WorkGraph Reference](https://docs.rkat.ai/reference/workgraph-reference.md): WorkGraph item fields, statuses, edges, evidence, tools, and host surfaces.
- [Hooks reference](https://docs.rkat.ai/reference/hooks-reference.md): Low-level hook surface reference: hook points, capabilities, execution modes, and payload fields.
- [Skills reference](https://docs.rkat.ai/reference/skills-reference.md): Low-level skill runtime reference: source transports, identity, injection paths, and discovery tools.
- [Structured output reference](https://docs.rkat.ai/reference/structured-output-reference.md): Low-level structured-output reference: schema types, compatibility modes, warnings, and result fields.
- [Comms Reference](https://docs.rkat.ai/reference/comms-reference.md): Exact comms surface, identity, message, taint, reply-capability, ingress, and observation contracts.
- [Capability matrix](https://docs.rkat.ai/reference/capability-matrix.md): Build profiles, feature gates, error codes, and capability behavior across Meerkat configurations.
- [Session contracts](https://docs.rkat.ai/reference/session-contracts.md): Canonical session, runtime, keep-alive, and commit-boundary contracts.
- [Usage accounting](https://docs.rkat.ai/reference/usage-accounting.md): Per-call vs session-cumulative token usage, per-model attribution on the event stream, and the aggregation that does not double-count.
- [Skills Governance Runbook](https://docs.rkat.ai/reference/skills-governance-runbook.md): Operational runbook for source UUID lifecycle, lineage migrations, and remap governance.
- [Architecture](https://docs.rkat.ai/reference/architecture.md): A high-level map of Meerkat's runtime, surfaces, machines, storage, providers, and orchestration model.
- [Runtime Architecture](https://docs.rkat.ai/reference/runtime-architecture.md): How Meerkat routes session work through runtime-backed surfaces, session services, and the agent factory.
- [Machine Authority](https://docs.rkat.ai/reference/machine-authority.md): The canonical machine catalog, generated artifacts, and validation gates that keep runtime semantics aligned with code.
- [Mob Architecture](https://docs.rkat.ai/reference/mob-architecture.md): Mob authority, stable identity, local and placed execution, durable role migration, observation, flows, and operator surfaces.
- [Design Philosophy](https://docs.rkat.ai/reference/design-philosophy.md): The engineering principles behind Meerkat's runtime, API boundaries, Rust implementation style, and validation model.
- [Meerkat Dogma](https://docs.rkat.ai/architecture/meerkat-dogma.md): Primary runtime architecture doctrine for semantic authority, seams, projections, and surfaces.
- [Meerkat Dogma Commentary](https://docs.rkat.ai/architecture/meerkat-dogma-commentary.md): Companion commentary with examples, repair shapes, and review questions for Meerkat dogma.
- [Durable Instruction Activation](https://docs.rkat.ai/architecture/durable-instruction-activation.md): Architecture decision for reproducible instruction evolution in durable sessions.
- [Delivery, Interaction, and Durable Operations](https://docs.rkat.ai/architecture/delivery-interaction-operations.md): Architecture decision separating one-way comms delivery, conversational interaction, and machine-owned durable operations.
- [Realm Config Inheritance Plan](https://docs.rkat.ai/architecture/realm-config-inheritance-plan.md): Historical implementation record for deterministic realm configuration inheritance and credential provenance.
- [Multi-Host Mobs Plan](https://docs.rkat.ai/architecture/multi-host-mobs-plan.md): Implemented multi-host mob architecture and its preserved v4.1 adjudication and implementation record.
- [Stopped-Phase Revival](https://docs.rkat.ai/architecture/stopped-phase-revival-plan.md): Root-cause design record for the 0.7.19–0.7.23 resume-strand class: machine-owned revival of stopped sessions and cold-load snapshot reconciliation
- [WorkGraph Attention Goals](https://docs.rkat.ai/architecture/workgraph-attention-goals.md): Implemented architecture for Codex-style goals without duplicating WorkGraph or leaking mob semantics into core.
- [Storage Unification Plan](https://docs.rkat.ai/plans/storage-unification-plan.md): Implemented design record for Meerkat's path authority, shared SQLite mechanics, storage-provider seam, diagnosis, and fenced migration framework.
- [Durable Tool Execution and Background Jobs v1](https://docs.rkat.ai/plans/durable-tool-execution-and-background-jobs-v1.md): Historical architecture and delivery record for durable detached tools, generated job lifecycle authority, recovery, delivery, and host protocols.
- [Member Tool Policy v1](https://docs.rkat.ai/plans/member-tool-policy-v1.md): Proposal for durable per-member tool materialization, conjunctive execution constraints, and an early consequence-narrowing seam.
- [Durable Tool Execution v1 Deferred Findings](https://docs.rkat.ai/plans/durable-tool-execution-and-background-jobs-v1-deferred-findings.md): Deferred findings discovered while delivering the durable tool execution and background jobs plan.
- [Durable Tool Execution Deferred Findings](https://docs.rkat.ai/plans/durable-tool-execution-deferred-findings.md): Earlier deferred findings from the durable shell and job execution delivery slices.
- [Storage Operations](https://docs.rkat.ai/guides/storage-operations.md): Diagnose realm storage, run fenced offline migrations, resolve split-brain roots, bridge historical SQLite realms, and prune registered backups.
- [Build And CI](https://docs.rkat.ai/reference/build-and-ci.md): The Make, Cargo, BuildBuddy, and release validation surfaces used by Meerkat contributors.
- [CD and distribution](https://docs.rkat.ai/guides/cd-and-distribution.md): How Meerkat release artifacts are validated, built, and published across Rust, binaries, Python, and TypeScript.
- [Introduction](https://docs.rkat.ai/mobkit/introduction.md): MobKit is the application gateway, policy, SDK, persistence-projection, and console layer for Meerkat agents and mobs.
- [Quickstart](https://docs.rkat.ai/mobkit/quickstart.md): Bootstrap a MobKit runtime with modules and a Meerkat mob. Single binary, operational from the first call.
- [Modules](https://docs.rkat.ai/mobkit/concepts/modules.md): Subprocess capability boundaries, core MCP tools, discovery, and startup supervision.
- [Events](https://docs.rkat.ai/mobkit/concepts/events.md): Unified agent and module envelopes, structural mob events, lossy WorkGraph wakes, ordering, and runtime lifecycle stages.
- [Roster and member lifecycle](https://docs.rkat.ai/mobkit/concepts/roster.md): Understand MobKit's lightweight roster projection, deep member status, lifecycle states, and mutation results.
- [Gating](https://docs.rkat.ai/mobkit/concepts/gating.md): Runtime-owned R0-R3 policy evaluation, pending approvals, safe-draft fallback, and audit records.
- [Access control](https://docs.rkat.ai/mobkit/concepts/access-control.md): Optional ABAC for the console: control which users can see which agents and what they can do with them, configurable live per user. Plus scoped grants for peer gateways on the cross-mob control channel.
- [Delivery](https://docs.rkat.ai/mobkit/concepts/delivery.md): Trusted route resolution and MCP-backed delivery with optional bounded idempotency and fixed-window rate limits.
- [Scheduling](https://docs.rkat.ai/mobkit/concepts/scheduling.md): Durable schedule ownership, occurrence claims, firing, and target delivery.
- [Memory](https://docs.rkat.ai/mobkit/concepts/memory.md): Operational memory assertions plus optional identity-first agent memory injection.
- [Sessions](https://docs.rkat.ai/mobkit/concepts/sessions.md): How MobKit's session-store adapters relate to Meerkat's canonical runtime-backed session lifecycle.
- [Unified Runtime](https://docs.rkat.ai/mobkit/guides/unified-runtime.md): Combine a Meerkat mob with MobKit modules into a single managed runtime with merged events and coordinated lifecycle.
- [Module System](https://docs.rkat.ai/mobkit/guides/module-system.md): Route module calls, select MCP or event-line boundaries, and inspect module startup health.
- [Console](https://docs.rkat.ai/mobkit/guides/console.md): Embedded MobKit console with configurable branding, grouped roster, chat workspace, timeline replay, signals, logs, and operator controls.
- [Flow Editor](https://docs.rkat.ai/mobkit/guides/flow-editor.md): Embedded visual mobpack authoring studio with Basic and Graph editing modes, server-authoritative drafts, rkat-backed validation, and gated host deploys.
- [Authentication](https://docs.rkat.ai/mobkit/guides/authentication.md): JWT validation, OIDC discovery, provider configuration, and email allowlist enforcement.
- [JSON-RPC](https://docs.rkat.ai/mobkit/api/rpc.md): JSON-RPC 2.0 protocol for MobKit runtime operations: gating, memory, routing, delivery, sessions, and subscriptions.
- [REST API](https://docs.rkat.ai/mobkit/api/rest.md): HTTP endpoints for console access, experience metadata, module inspection, timeline replay, JSON-RPC ingress, and blobs.
- [SSE API](https://docs.rkat.ai/mobkit/api/sse.md): Server-Sent Events for real-time MobKit interaction and event subscription flows.
- [Rust SDK](https://docs.rkat.ai/mobkit/sdks/rust.md): Use MobKit as a Rust library: bootstrap runtimes, route module calls, and manage operational subsystems programmatically.
- [TypeScript SDK](https://docs.rkat.ai/mobkit/sdks/typescript.md): TypeScript SDK for MobKit with type-safe contracts, parity tests, and ESM/CommonJS support.
- [Python SDK](https://docs.rkat.ai/mobkit/sdks/python.md): MobKit Python SDK — typed builder API, async runtime, and streaming events.
- [Architecture](https://docs.rkat.ai/mobkit/reference/architecture.md): MobKit ownership boundaries, gateway profiles, composition, storage projections, module routing, console surfaces, and security.
- [Configuration](https://docs.rkat.ai/mobkit/reference/configuration.md): Configuration reference for MobKit: module definitions, runtime options, auth policies, and session stores.
- [Decisions](https://docs.rkat.ai/mobkit/reference/decisions.md): Policy enforcement: auth rules, console access, runtime ops constraints, release validation, and BigQuery naming.
- [Governance](https://docs.rkat.ai/mobkit/reference/governance.md): Release candidate tracking, traceability matrix, validation, and governance state contracts.