
seshka
In short: seshka is an open-source coding AI tool. Free, MIT-licensed macOS menu bar app that cleans up after Claude Code. X Buzz Score: 21/100 (21 posts in 7 days).
Verdict: Free, MIT-licensed macOS menu bar app that cleans up after Claude Code. When a session ends, the dev servers, file watchers and emulators it started often keep running. seshka lists them grouped by session, with port, memory and age, and kills them in one click, telling you how much memory you got back. It can also end idle Claude Code sessions by hand or after a time limit you set; you bring them back with claude --resume. Needs macOS 14 or later. It's a brand-new project from the JigJoy team (repo created Nov 13, 2026, under 10 GitHub stars, #9 on Product Hunt Nov 17), so expect rough edges.
Use this if you run several Claude Code sessions on a Mac and keep finding old dev servers hogging ports and memory.
Live X Buzz Score
X 21/100 Quiet updated 20 Nov, 09:16 HKT
Daily X posts, last 7 days (oldest → today): 0 · 0 · 0 · 0 · 7 · 11 · 3. Score parts: volume 13.4/50, spike 0/25, engagement 7.9/25. Method
No standout X posts yet (we only show posts with 100+ likes or 10K+ views).
Alternatives
- Claude Code: Terminal-based coding agent that edits and runs your repo.
- Worktrunk: CLI for Git worktrees built for running several AI coding agents in parallel: create, switch, merge and clean up a worktree per agent with short commands. Open source (github.com/max-sixty/worktrunk), v0.81.0 released Oct 20 2026; ~440 stars in a day on GitHub trending Nov 4 (~10.5K total). Assumes you are comfortable with git and the terminal.
- Termy: Mac notch terminal for Claude Code and Codex: live working/needs-you/done status from real hooks, Allow/Deny in the notch, persistent sessions, Agent Office and Whisper dictation on Pro. Free; Pro $4.99 one-time. Needs macOS 26 (notch optional — menu bar works). Overlaps with SKI on agent UX; Termy is the drop-down terminal, not a voice harness.
Similar AI tools
- Gemini 4 Neon: Google's 18 Nov 2026 Gemini 4 model, aimed at fast end-to-end software engineering, knowledge work and science. API price is $3 in / $15 out per million tokens ($0.15 cached input) with a 1M-token context window. It is rolling out in the Gemini API and AI Studio on the paid tier, in Gemini for business, and to Google AI Pro and Ultra subscribers in Antigravity and the Gemini app — not described as a free-tier default. Google reports a 61 on the Artificial Analysis Intelligence Index at its xhigh thinking level and #1 on that firm's Coding Agent Index; treat those as Google's claims. In Antigravity it can also orchestrate parallel Gemini 4 Hydrogen subagents.
- Claude: Excellent for long documents, writing and careful coding help.
- OpenCode 2.0: Open-source, model-agnostic terminal coding agent with a native TUI and multi-session support.
- GPT-6.2 Astra: OpenAI's new top model for hard professional work, released Nov 17, 2026. OpenAI says it makes slides, spreadsheets and documents that follow your templates more closely and 'read less like AI', and that it writes cleaner code, especially for websites, games and 3D design. It's in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users (not the free plan), and in the API as gpt-6.2-astra at $8 in / $40 out per million tokens, 20% less than GPT-6 Astra. Artificial Analysis puts it second on its Intelligence Index, just behind Claude Fable 5.2. Early testers on X report mixed results on long tasks, and OpenAI's system card says it was more likely than its predecessor to leave out obstacles when reporting its work, so check what it tells you it did.
- GPT-6.2 Sol: OpenAI's faster, cheaper everyday model, released Nov 17, 2026 alongside GPT-6.2 Astra. OpenAI says it is smarter and more token-efficient than GPT-6.1 Sol, handles multistep agent workflows well, and that many OpenAI staff use it as their default. It's in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users, and Pro 200 subscribers get the Ultrafast mode with Sol for the first time. In the API it's gpt-6.2-sol at the same price as 6.1 Sol: $2 in / $10 out per million tokens ($0.10 cached input), about a fifth of Astra's token price. The quality claims are OpenAI's own.
- ChatGPT: The default general assistant; strong all-rounder with a huge plugin and GPT ecosystem.
See all: best AI tools for coding · trending AI tools today
FAQ
What is seshka?
Free, MIT-licensed macOS menu bar app that cleans up after Claude Code. When a session ends, the dev servers, file watchers and emulators it started often keep running. seshka lists them grouped by session, with port, memory and age, and kills them in one click, telling you how much memory you got back. It can also end idle Claude Code sessions by hand or after a time limit you set; you bring them back with claude --resume. Needs macOS 14 or later. It's a brand-new project from the JigJoy team (repo created Nov 13, 2026, under 10 GitHub stars, #9 on Product Hunt Nov 17), so expect rough edges.
Who should use seshka?
Use seshka if you run several Claude Code sessions on a Mac and keep finding old dev servers hogging ports and memory.
Is seshka free?
Yes. seshka is open source, so you can use and self-host it for free. Any hosted version or the AI model it calls may cost extra.
What are alternatives to seshka?
Alternatives include Claude Code, Worktrunk, Termy, Gemini 4 Neon.
Get your badge: maker of seshka? Add a free "Featured on toolhype" badge
HTML (light)
<a href="https://toolhype.dev/tools/seshka" target="_blank"><img src="https://toolhype.dev/badge/featured-light.svg" alt="seshka is featured on toolhype" width="220" height="54" /></a>Markdown (light)
[](https://toolhype.dev/tools/seshka)HTML (dark)
<a href="https://toolhype.dev/tools/seshka" target="_blank"><img src="https://toolhype.dev/badge/featured-dark.svg" alt="seshka is featured on toolhype" width="220" height="54" /></a>Markdown (dark)
[](https://toolhype.dev/tools/seshka)Discussion
Comments are coming with sign-in.