From 2cf4687231438056099466c4bd7e3b5916b67525 Mon Sep 17 00:00:00 2001 From: isamu Date: Mon, 14 Sep 2026 17:01:14 +0900 Subject: [PATCH 1/2] Add MulmoTerminal to AI & Context Efficiency Co-Authored-By: Claude Opus 5 (1M context) --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 32b8bce..35102f6 100644 --- a/README.md +++ b/README.md @@ -22,6 +22,8 @@ Open-source, local-first, small, composable, and single-purpose tools are prefer - [YYLO](https://github.com/yylo-dev/yylo) - Command-line orchestrator that runs each coding-agent task in a dedicated branch/worktree with typed validation and merge boundaries, reducing context overhead and repetitive review work. +- [MulmoTerminal](https://github.com/receptron/mulmoterminal) - Browser grid of live Claude Code / Codex sessions, each cell a real PTY colour-coded working / needs-you / done from the agent CLI's own hooks, so a session blocked on a permission prompt is distinguishable from one still thinking without opening it. tmux-backed, git worktree per cell, one `npx` command. + - [OrcaReplay](https://github.com/Continuum-AI-Corp/OrcaReplay) - Records a coding-agent run below the harness — model traffic, shell exit codes, per-turn file changes and MCP calls on one timeline — then replays it offline with the network off, or forks it from a checkpoint onto a different model. ## Build & Test Efficiency From 5f64cecb719e44d5e588b7c286cef6c2634036be Mon Sep 17 00:00:00 2001 From: isamu Date: Tue, 15 Sep 2026 09:14:31 +0900 Subject: [PATCH 2/2] Simplify MulmoTerminal description per review --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 35102f6..bcadc9b 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ Open-source, local-first, small, composable, and single-purpose tools are prefer - [YYLO](https://github.com/yylo-dev/yylo) - Command-line orchestrator that runs each coding-agent task in a dedicated branch/worktree with typed validation and merge boundaries, reducing context overhead and repetitive review work. -- [MulmoTerminal](https://github.com/receptron/mulmoterminal) - Browser grid of live Claude Code / Codex sessions, each cell a real PTY colour-coded working / needs-you / done from the agent CLI's own hooks, so a session blocked on a permission prompt is distinguishable from one still thinking without opening it. tmux-backed, git worktree per cell, one `npx` command. +- [MulmoTerminal](https://github.com/receptron/mulmoterminal) - Browser grid for parallel coding-agent sessions with real PTYs, status indicators, tmux persistence, and git-worktree isolation, reducing attention switching and missed agent prompts. - [OrcaReplay](https://github.com/Continuum-AI-Corp/OrcaReplay) - Records a coding-agent run below the harness — model traffic, shell exit codes, per-turn file changes and MCP calls on one timeline — then replays it offline with the network off, or forks it from a checkpoint onto a different model.