AI Developer Tool / CLI / Dev Workflow

claude-thermos

A local CLI tool that keeps Claude Code sessions warm by refreshing prompt cache during long subagent runs, aiming to reduce re-encoding costs in extended sessions.

Clear28/30
Useful26/30
Specific16/20
Complete13/20
claude-thermos screenshot

Why it was accepted

The page clearly describes a real AI developer tool with a specific job: keeping Claude Code prompt caches warm during long sessions. The README shows how it works, how to run it with uvx, the Python and Claude CLI requirements, tuning flags, logs, and the savings model, which is enough evidence for a useful public listing.

Weakness

The crawl does not show install instructions beyond the uvx command, tests or release status, or support for anything outside Claude Code. It also isn’t clear how much setup is needed for first-time use beyond having Python 3.11+ and the Claude CLI installed.

Review status

106 days ago #1572 ↓ -3

Last evaluated 106 days ago. Current rank #1572. Down 3 spots in the rankings.

Score history

83

Related listings

Sidefleet screenshot
#38 Sidefleet
90

AI Developer Tool / Coding Agents / Orchestration

Sidefleet is a self-hosted control plane for running coding agents across your own machines. It routes tasks to the least busy machine with the right repo and agent, runs work in isolated git worktrees, streams progress live, and supports Claude Code, Codex, and opencode.

prompt-scrub screenshot
90

AI Developer Tool / Prompt privacy / PII redaction

A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.

Tessary screenshot
#127 Tessary
89

AI Developer Tool / Agent reliability / observability

Open-source platform for monitoring AI agents in production, detecting failures, grouping incidents into cases, and investigating root causes with trace and repository evidence.

ORBIT screenshot
#177 ORBIT
89

AI Developer Tool / AI Gateway / RAG Backend

Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents. It connects files, databases, vector stores, APIs, and MCP tools through one backend with auth, observability, and governance features.