Agent Analytics and Utilities

Observability, token optimization, and code indexing tools for AI coding agent workflows.

Parent: Agentic Development Tools


Agentlytics — Session Analytics Dashboard

Repogithub.com/f/agentlytics (Fatih Kadir Akin)
LanguageJavaScript (Node.js backend) + React 19 SPA (Vite + Tailwind)
WhatRead-only analytics dashboard for AI coding sessions across 16 editors
Maturity167 commits in 5 days, v0.2.8, macOS only, no tests

Reads session data from Cursor, Windsurf, Claude Code, VS Code Copilot, Zed, Gemini CLI, Codex, and more by parsing their local storage files (JSONL, SQLite, ConnectRPC). Normalizes into a local SQLite cache, serves a web dashboard at localhost:4637.

Features: KPIs, cost estimation, token usage, model/tool breakdowns, activity heatmaps, coding streaks, subscription/quota tracking, per-project analytics, editor comparison, SQL viewer for direct cache queries.

Relevance: useful for understanding token costs across all your editors. The subscription tracking (reads Keychain auth tokens to query Anthropic/Cursor/Copilot APIs) could help manage the limited-tokens home setup.


Distill — Token Compression Pipe Filter

Repogithub.com/samuelfaj/distill
LanguageTypeScript/Bun, distributed as native platform binaries via npm
WhatPipe verbose command output through a local LLM to compress it before feeding back to an expensive model
Maturity29 commits over 6 days, v1.4.1

bun test 2>&1 | distill "Did the tests pass?" — claims up to 99% token savings. Default backend: Ollama with qwen3.5:2b. Supports 11 LLM providers.

Modes: batch (one-shot summarization), watch (auto-detects repeating output, reports diffs), interactive passthrough (detects [y/N] prompts). Bad distillation detection falls back to raw output.

Relevance: useful at home with limited tokens. Each Claude Code session could pipe verbose outputs through distill. Requires a local model (Ollama).


jcodemunch-mcp — Token-Efficient Code Indexing

Repogithub.com/jgravelle/jcodemunch-mcp
LanguagePython 3.10+
WhatMCP server that indexes codebases with tree-sitter, provides O(1) symbol retrieval instead of loading entire files
Maturity245 commits, v1.5.1, 5+ contributors, dual license (free personal / paid commercial)

Instead of an agent reading 40,000 tokens to find one function, it reads ~200 tokens via search_symbols then get_symbol. Supports 30+ languages via tree-sitter.

Features: 14+ MCP tools, incremental re-indexing (hash-based change detection), stable symbol IDs, multiple transports (stdio, SSE, HTTP), bearer token auth for HTTP mode.

Relevance: direct token saver for Claude Code sessions. Configure as MCP server per project. The 30+ language support covers Go, Rust, Python, TypeScript — all relevant to your work.


Open Terminal — Remote Terminal API

Repogithub.com/open-webui/open-terminal (Open WebUI org)
LanguagePython 3.11+ (FastAPI + Uvicorn)
WhatHeadless API server that gives AI agents a sandboxed environment for shell commands, file management, Jupyter execution
Maturity128 commits, v0.11.20, by Timothy Jaeryang Baek (Open WebUI creator)

REST API for command execution, file CRUD, WebSocket interactive terminals (xterm.js compatible), Jupyter notebook cell execution. MCP server mode exposes all endpoints. Multi-user isolation with per-user Linux accounts. Network egress filtering via dnsmasq + iptables.

Relevance: could provide sandboxed execution environments for agents. The network egress filtering is interesting given the sandbox constraints on your work Mac. However, it’s a complementary execution backend, not a session manager.


Quick Reference

ToolPurposeToken savingsMCPEffort to adopt
AgentlyticsAnalytics dashboardIndirect (visibility)NoLow (just install + run)
DistillCompress command outputDirect (up to 99%)NoLow (pipe filter)
jcodemunch-mcpCode indexingDirect (~95% per lookup)Yes (14 tools)Medium (index per project)
Open TerminalSandboxed executionNoneYesHigh (server deployment)