Prime Agent Documentation

Pages

1. OverviewWhat Prime Agent exposes, primary entry points (CLI, SDK, modes), runtime assumptions, and the first docs routes to follow.
2. InstallationStable install command, release checksum flow, prime-agent binary placement, IPython runtime prep, and first-launch success signals.
3. QuickstartStart prime-agent in a project directory, complete onboarding, run a first task, and verify interactive session health.
4. Authentication and providersLogin and API-key paths, multi-provider selection, OAuth examples, auth error recovery, and BYOK provider boundaries.
5. RLM control planeRecursive Language Model model: persistent IPython as the control tool, prompt-as-variable context, and rlm(...) subagent calls.
6. Continual HarnessDurable harness state (prompts, memories, skill specs, subagent specs), refine boundaries, immutable base prompt, and rollback snapshots.
7. Sessions and runtimeAgent session lifecycle, session services, runtime events, queueing, tree navigation, and session-scoped vs durable state.
8. Skills modelSkills as importable Python packages, SKILL.md frontmatter constraints, collision precedence, and project vs personal skill scope.
9. Subagents and messagingrlm-spawned child agents, agent-message skill surface, direct agent-to-agent communication, and multi-agent orchestration constraints.
10. Run daemon-backed sessionsBackground daemon client modes, active session state, detach and reattach, resume selectors, and worker recovery verification.
11. Create and install skillsAuthor a skill package with skill-creator, required SKILL.md fields, Python package layout, and load-path verification.
12. Refine harness stateRun /refine against the current trajectory, apply evidence-backed harness updates, serialize refine, and use snapshots for rollback.
13. Long-running tasksGoals, compaction, heartbeats, autonomous mode, and retained subagents that keep multi-turn work progressing across disconnects.
14. Use ACP modeRun the Agent Client Protocol mode, map cold CLI launch, feature flags, stop reasons, and cwd constraints for editor integrations.
15. Extensions and custom toolsRegister extensions, custom tools, plan-mode and subagent extension samples, allowlists, and dynamic resource patterns.
16. Session configuration referenceAgent session config keys, defaults, reload behavior, in-memory settings, and config surfaces used by runtime services.
17. Settings and provider keysProvider registration, model selection, API key and OAuth wiring, dynamic provider updates, and 401 stale-provider recovery.
18. Built-in skills referenceCatalog of shipped skills (goal, refine, compact, heartbeat, observe, message, edit, integrations) with entry modules and invocation roles.
19. Agent connection modesDaemon, in-process, and snapshot connection paths; agents-view mode; active session state and transfer idempotency constraints.
20. ACP protocol referenceACP mode entrypoints, event types, meta fields, stop reasons, kernel features, and protocol-facing constraints from source and tests.
21. Minimal SDK agentCopy-paste minimal SDK bootstrap, custom prompt and model wiring, and expected first-run output from examples.
22. Skills, tools, and extensionsSDK recipes for loading skills, registering tools, extensions, context files, prompt templates, and subagent extension wiring.
23. Sessions and full controlSDK session management, settings injection, session runtime hooks, and the full-control composition example.
24. TroubleshootingAuth failures, invalid resume selectors, provider 401s, network retry, worker recovery, and connection-mode failure probes.
25. Develop from sourceMonorepo workspaces, build and check scripts, package boundaries (ai, agent, coding-agent, tui), and contributor conventions from AGENTS.md.