MANUAL
Guidance on how to thrive in the swamp.
Swamp is an adaptive automation framework designed to be operated by AI Agents. Start by reading How Swamp Works if you're just getting started.
Create and Publish an Extension
Create a TypeScript extension, validate it locally, publish it to the swamp registry under your collective, and install it in another repo.
How-to Guides →Use Swamp with Claude Code
Initialize a swamp repository for Claude Code with native skill support, permissions, and audit hooks
How-to Guides →Use Swamp with Codex
Initialize a swamp repository for OpenAI Codex with skill discovery and AGENTS.md instructions
How-to Guides →Use Swamp with OpenCode
Initialize a swamp repository for OpenCode with skill discovery, AGENTS.md instructions, and audit plugin
How-to Guides →Use Swamp with Kiro
Initialize a swamp repository for Kiro with skill discovery, steering rules, agent config, and audit hooks
How-to Guides →Use Swamp with Cursor
Initialize a swamp repository for Cursor with skill discovery, rules file, and audit hooks
How-to Guides →Use Swamp with Copilot
Initialize a swamp repository for GitHub Copilot with skill discovery and AGENTS.md instructions
How-to Guides →Improve Your Extension Score
Per-factor fixes for raising an extension's quality score — README content, JSDoc coverage, type annotations, license, repository verification, and rescoring
How-to Guides →CEL Expressions
Complete reference for CEL expression syntax, context variables, operators, functions, and data queries in swamp
Reference →Model Definitions
Complete YAML schema reference for swamp model definitions — fields, types, defaults, constraints, and validation rules
Reference →OpenTelemetry
Reference for OpenTelemetry configuration, span hierarchy, context propagation, and instrumentation points in swamp
Reference →Workflows
Complete YAML schema reference for swamp workflows — jobs, steps, tasks, dependencies, triggers, forEach iteration, and execution ordering
Reference →Vaults
Complete reference for swamp vaults — types, creation, key storage, retrieval, CEL integration, encryption, and environment variable mounting
Reference →Data Outputs
Reference for swamp data outputs: resource and file specs, lifetime, garbage collection, versioning, streaming, tags, sensitive fields, and CLI
Reference →Repository Configuration
Complete YAML schema reference for .swamp.yaml — every field, type, default, environment variable override, and validation rule
Reference →Extension Manifest
Complete YAML schema reference for swamp extension manifests — every field, type, constraint, path resolution rule, and push validation
Reference →Data Querying
Reference for swamp data query: CEL predicates, DataRecord fields, --select projections, tag filtering, data.query() in expressions, and interactive TUI
Reference →Datastore Configuration
Reference for swamp datastore backends, configuration fields, environment variable overrides, sync behavior, distributed locking, and CLI commands
Reference →Extension Scorecard Rubric
Factors, point values, and earning conditions for the extension quality score, grade thresholds, repository verification hosts, and the Verified by Swamp badge
Reference →Notifications
What triggers a Lab inbox notification, how mentions are parsed, the dedup and rate-limit rules, and scope caveats.
Reference →How Swamp Works
How models, workflows, vaults, extensions, skills, and data querying compose into agent-driven automation
Explanation →AI Agent Integration
Why swamp is designed around AI agents, how the agent interface works, and what makes different tools effective with swamp
Explanation →About the Extension Scorecard
What the extension quality score measures, why it exists, where it appears, and why Verified by Swamp is a separate badge rather than a scored factor
Explanation →