lm-assist

lm-assist

The Observability Platform for Claude Code & Agent SDK

Monitor, debug, and control AI coding agents with full session visibility, real-time execution tracking, and 155+ REST API endpoints.

• Monitor — real-time execution tracking, per-model cost & token breakdown, SSE event stream
• Debug — 15 insight views per session: Chat, Thinking, Agents, Plans, Team, DAG, Files, Git & more
• Control — web terminal from any browser, start/abort agents via API, remote access from anywhere

Install

/plugin marketplace add langmartai/lm-assist
/plugin install lm-assist@langmartai

Then open a new Claude Code session and run /assist-setup.

Read: Inside Claude Code: The Session File Format and How to Inspect It — technical breakdown of the JSONL session format, message types, subagent trees, and how lm-assist surfaces it all.

---

Why lm-assist

Claude Code and the Agent SDK have no built-in dashboard. You get a terminal or logs. When you're running multiple agents, debugging a failed execution, or tracking costs across a fleet of machines — you need full visibility into every session, every subagent, every tool call, every token spent.

Without lm-assist	With lm-assist
Scroll through terminal output	15 specialized views per session
No cost visibility	Per-model token & cost breakdown
Can't see what agents are doing	Real-time execution dashboard
No way to inspect subagent trees	Full DAG visualization
Terminal-only access	Web UI from any device, anywhere
Agent SDK runs are black boxes	Same session inspection as CLI

---

Three Pillars

1. Monitor

Real-time execution tracking via REST API.

• Session list with slug names, live status, running process detection
• Per-session and per-project cost tracking with per-model token breakdown
• SSE event stream for real-time updates (GET /stream)
• Multi-machine fleet dashboard via LangMart Hub
• Statusline: context %, rate limits (5h/7d), cost, RAM, PID

Key endpoints: GET /monitor/executions · GET /stream · GET /sessions · GET /projects/sessions

2. Debug

15 data dimensions per session, all accessible via API.

• Conversation, thinking blocks, tool calls, subagent hierarchy, DAG
• File changes, git operations, plans, tasks, team coordination
• Fork tracking, session summaries, skill traces

Key endpoints: GET /sessions/:id · GET /sessions/:id/dag · GET /sessions/:id/subagents · GET /sessions/:id/conversation

3. Control

Full runtime management API.

• Start and abort agent executions
• SDK runner for programmatic headless execution
• Session cache warm/clear
• Web terminal (ttyd) from any browser
• Remote access via LangMart Hub

Claude Code OAuth (14 endpoints) — proxies api.anthropic.com using Claude Code's OAuth token from ~/.claude/.credentials.json. See docs/claude-code-routes.md for the full per-endpoint reference. Quick map: /claude-code/{oauth-status, usage, profile, roles, account-settings, cli-bootstrap, grove, penguin, policy-limits, settings, user-settings, team-memory, mcp-servers, mcp-registry}.

claude.ai web-session (28 endpoints) — proxies claude.ai's web backend via a cookie file OR a real Chrome tab through MCP. See docs/claude-ai-routes.md for both paths, the health-check interface, and the via-chrome agent loop pattern. Quick map: /claude-ai/{healthz, account-profile, conversations[/:uuid[/{completion,title}]], projects, memory, bootstrap, artifacts/:uuid/versions, org, org/{subscription, usage, skills, mcp-bootstrap, styles, model-config/:model, memory-settings, cowork-settings, sync-settings, sync/gdrive-progress, notifications}, account/invites, user-access, sessions-active} · POST /claude-ai/via-chrome[/...].

Other key endpoints: POST /monitor/abort/:executionId · POST /ttyd/start · POST /agent/execute · POST /agent/session/:sessionId/resume · POST /hub/connect

Web Dashboard

See claude-code-webui for the full web dashboard with 15 insight tabs, web terminal, task kanban, and mobile support.

---