claude-devtools
AgentFreeThe missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Capabilities12 decomposed
jsonl session log parsing with per-turn reconstruction
Medium confidenceParses Claude Code's JSONL session files stored at ~/.claude/projects/ to reconstruct the complete execution trace of each turn, including file reads, tool calls, token consumption, and context injections. Uses a streaming JSONL parser with caching strategy to handle large session files efficiently without loading entire logs into memory, enabling post-hoc analysis of sessions regardless of execution environment (terminal, IDE, or wrapper tool).
Implements streaming JSONL parsing with multi-level caching (file-level and turn-level) to reconstruct per-turn context windows without requiring full session file loads, combined with path encoding scheme (Project IDs) to handle complex project hierarchies and remote SSH paths uniformly
Provides deeper execution visibility than Claude Code's native --verbose output by structuring raw logs into queryable turn-by-turn traces, while avoiding the terminal flooding and raw JSON noise of verbose mode
context window composition analysis with token attribution
Medium confidenceReverse-engineers the per-turn context window contents by analyzing session logs and attributing tokens across discrete categories: CLAUDE.md files, skill activations, tool I/O, thinking blocks, and system prompts. Uses a token accounting system that maps each context component back to its source in the session log, enabling developers to understand exactly why the context window grew or shrank at each step.
Implements a multi-category token attribution system that maps context components back to their source in session logs, using Claude's tokenizer to provide accurate per-category breakdowns rather than opaque aggregate counts, combined with skill activation tracking to identify unused context
Provides granular context breakdown that Claude Code's native three-segment context bar cannot show, enabling developers to make informed decisions about project structure and skill organization
auto-update system with code signing and notarization
Medium confidenceImplements an auto-update mechanism using Electron's update framework with code signing (macOS) and notarization to ensure app integrity. Detects new releases from GitHub, downloads updates in the background, and prompts users to install with a visual dialog. Supports staged rollouts and rollback on update failures.
Implements Electron auto-update with code signing and macOS notarization to ensure update integrity, combined with a visual update dialog and support for deferred installation, enabling secure background updates
Provides automatic, secure updates with code signing and notarization, whereas manual downloads require user intervention and lack integrity verification
project scanner with path encoding and unified project id system
Medium confidenceScans the Claude projects directory to discover all projects and their sessions, using a path encoding scheme that creates stable Project IDs from file paths. Handles both local paths and remote SSH paths uniformly, enabling a single project ID to reference sessions across different machines. Caches project metadata to avoid repeated directory scans.
Implements a path encoding scheme that creates stable, deterministic Project IDs from file paths, enabling unified project identification across local and remote machines, combined with metadata caching to optimize repeated discovery
Provides a unified project namespace across local and remote machines using stable Project IDs, whereas naive approaches would require separate project lists per machine or complex path mapping
ssh remote session inspection with sftp file operations
Medium confidenceConnects to remote machines via SSH/SFTP to discover and parse Claude Code sessions running on remote servers, enabling inspection of remote session logs as if they were local. Implements an SSH Connection Manager that handles authentication (key-based and password), remote path resolution, and transparent SFTP file operations, with a caching layer to avoid repeated remote file transfers. Supports multi-machine setups where developers run Claude Code on different servers.
Implements a dedicated SSH Connection Manager with transparent SFTP file operations and multi-level caching (connection pooling, file content caching) to minimize latency, combined with path encoding scheme that unifies local and remote paths under a single Project ID system
Eliminates manual SSH workflows for inspecting remote Claude Code sessions by providing a unified UI for both local and remote sessions, with automatic connection management and caching to reduce network overhead
real-time session discovery and auto-refresh with file system watching
Medium confidenceMonitors the ~/.claude/projects/ directory (local and remote) for new or updated session files using file system watchers, automatically discovering new sessions and refreshing existing session data without requiring manual refresh. Implements a Project Scanner that enumerates project directories, detects new sessions, and triggers incremental JSONL parsing for updated files. Uses debouncing and throttling to prevent excessive re-parsing during rapid file writes.
Combines native file system watchers (local) with SFTP polling (remote) and implements debouncing/throttling at the parsing layer to prevent UI thrashing, using incremental JSONL parsing to update only changed turns rather than re-parsing entire sessions
Provides live session visibility without manual refresh, unlike static log viewers that require explicit reload, while avoiding the resource overhead of naive file watching by implementing intelligent debouncing and incremental parsing
interactive session timeline and turn-by-turn inspection ui
Medium confidenceRenders a visual timeline of session turns with expandable details for each turn, showing tool calls, file reads, token consumption, and context state. Implements a React-based UI with virtualization to handle sessions with hundreds of turns efficiently, combined with a command palette for quick navigation and filtering. Each turn can be expanded to show full tool call arguments, results, and context composition.
Implements React virtualization to render hundreds of turns efficiently without loading entire session into DOM, combined with a command palette for keyboard-driven navigation and a collapsible turn structure that shows context composition at each step
Provides interactive, searchable session inspection in a native desktop UI rather than raw JSON or terminal output, with virtualization enabling smooth navigation through large sessions that would be unwieldy in text editors
notification system with custom trigger rules and filtering
Medium confidenceImplements a configurable notification system that triggers alerts based on session events (e.g., tool call failures, context window near capacity, session completion). Uses a Notification Manager with a trigger system that evaluates conditions against session data and supports filtering/throttling to prevent notification spam. Notifications can be configured per-project or globally, with support for custom trigger expressions.
Implements a declarative trigger system with filtering and throttling that evaluates conditions against parsed session data, supporting both built-in triggers (completion, failure, context threshold) and custom expressions, with per-project configuration
Provides proactive monitoring of Claude Code sessions without requiring manual polling, with configurable triggers and filtering to reduce alert fatigue compared to naive notification systems
cost and token usage analytics with multi-session aggregation
Medium confidenceAggregates token usage and cost data across multiple sessions, projects, and time periods to provide analytics dashboards showing trends, per-project costs, and cost-per-task metrics. Implements a Session Analyzer that computes statistics from parsed session data and supports filtering by date range, project, or session type. Integrates with Claude API pricing to calculate estimated costs based on token counts.
Implements multi-level aggregation (per-session, per-project, per-time-period) with filtering and trend analysis, combined with Claude API pricing integration to provide estimated costs alongside token counts, enabling cost-aware optimization
Provides cost visibility across multiple sessions and projects in a single dashboard, whereas Claude Code's native output only shows per-session token counts without aggregation or cost estimation
ipc-based multi-context architecture with electron main/renderer separation
Medium confidenceImplements a multi-context system using Electron's IPC (Inter-Process Communication) to separate concerns between the main process (file I/O, SSH, session parsing) and renderer process (UI, visualization). Uses a service context API that abstracts file operations and session parsing behind IPC handlers, enabling the renderer to request data without direct file system access. Supports concurrent session parsing and SSH operations in the main process while keeping the UI responsive.
Implements a service context API abstraction layer over Electron IPC that provides type-safe handlers for file operations, SSH, and session parsing, enabling the renderer to request data without direct file system access while maintaining process isolation
Provides responsive UI with background processing through proper Electron architecture, avoiding the common pitfall of blocking the renderer with synchronous file I/O or SSH operations
configuration management with ipc-based settings persistence
Medium confidenceProvides a settings interface for configuring Claude root directory, SSH connections, notification triggers, and UI preferences, with IPC-based persistence to store configuration in the main process. Implements Config IPC Handlers that validate and persist settings to disk, with support for per-machine and per-user configuration. Includes automatic Claude root detection to simplify initial setup.
Implements IPC-based configuration handlers with automatic Claude root detection and support for multiple SSH connection profiles, storing configuration in a structured format with validation at the main process level
Provides a user-friendly settings UI for configuration instead of requiring manual JSON editing, with automatic Claude root detection to simplify setup for new users
http sidecar server for external integrations and webhooks
Medium confidenceExposes an HTTP API server running alongside the Electron app to enable external tools and integrations to query session data and trigger notifications. Implements REST endpoints for session queries, cost analytics, and notification triggers, with optional authentication. Enables integration with CI/CD pipelines, monitoring systems, and custom dashboards.
Implements a lightweight HTTP sidecar server that exposes parsed session data and analytics via REST endpoints, enabling external integrations without requiring direct file system access, with optional authentication for security
Enables integration with external tools and CI/CD pipelines through a standard HTTP API, whereas the desktop UI alone is isolated and cannot be queried programmatically
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with claude-devtools, ranked by overlap. Discovered automatically through the match graph.
partial-json
Parse partial JSON generated by LLM
ccstatusline
🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.
CoWork-OS
Operating System for your personal AI Agents with Security-first approach. Multi-channel (WhatsApp, Telegram, Discord, Slack, iMessage), multi-provider (Claude, GPT, Gemini, Ollama), fully self-hosted.
ai-pdf-chatbot-langchain
AI PDF chatbot agent built with LangChain & LangGraph
langfuse
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
codeburn
See where your AI coding tokens go. Interactive TUI dashboard for Claude Code, Codex, and Cursor cost observability.
Best For
- ✓Claude Code users debugging agent behavior without access to --verbose output
- ✓Teams auditing LLM token consumption and session costs
- ✓Developers building Claude Code wrappers or integrations who need visibility into session execution
- ✓Claude Code users optimizing context usage for cost and performance
- ✓Developers analyzing skill activation patterns to improve project organization
- ✓Teams building Claude Code extensions who need to understand context impact
- ✓End users wanting automatic updates without manual intervention
- ✓Teams requiring code-signed and notarized binaries for security compliance
Known Limitations
- ⚠Requires session files to already exist on disk — cannot intercept live Claude Code execution
- ⚠Parsing accuracy depends on Claude Code's JSONL schema remaining stable; breaking schema changes require parser updates
- ⚠Large session files (>100MB) may cause UI lag during initial parsing despite caching strategy
- ⚠Cannot reconstruct context for sessions older than Claude Code's JSONL logging introduction
- ⚠Token attribution is approximate — uses Claude's tokenizer but may differ from actual API tokenization by ±5%
- ⚠Cannot attribute tokens to thinking blocks if Claude Code's logging omits thinking content
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
Last commit: Apr 18, 2026
About
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Categories
Alternatives to claude-devtools
Are you the builder of claude-devtools?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →