claude-code-tools VS .tmux

This sounds very promising. Using multiple CC instances (or mix of CLI-agents) across tmux panes has always been a workflow of mine, where agents can use the tmux-cli [1] skill/tool to delegate/collaborate with others.

This new orchestration feature makes it much more useful since they share a common task list and the main agent coordinates across them.

[1] https://github.com/pchalasani/claude-code-tools?tab=readme-o...

in your ~/.claude/settings.json, otherwise CC's telemetry pings cause total network failure because local ports are exhausted.

[1] claude-code-tools local LLM setup: https://github.com/pchalasani/claude-code-tools/blob/main/do...

As others said this was possible for months already with llama-cop’s support for Anthropic messages API. You just need to set the ANTHROPIC_BASE_URL. The specific llama-server settings/flags were a pain to figure out and required some hunting, so I collected them in this guide to using CC with local models:

https://github.com/pchalasani/claude-code-tools/blob/main/do...

One tricky thing that took me a whole day to figure out is that using Claude Code in this setup was causing total network failures due to telemetry pings, so I had to set this env var to 1: CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC

Curious how it compares to last week’s release of Kyutai’s Pocket-TTS [1] which is just 100M params, and excellent in both speed and quality (English only). I use it in my voice plugin [2] for quick voice updates in Claude Code.

[1] https://github.com/kyutai-labs/pocket-tts

[2] https://github.com/pchalasani/claude-code-tools?tab=readme-o...

Specifically for coding agents, one issue is how to continue work when almost fill the context window.

Compaction always loses information, so I use an alternative approach that works extremely well, based on this almost silly idea — your original session file itself is the golden source of truth with all details, so why not directly leverage it?

So I built the aichat feature in my Claude-code-tools repo with exactly this sort of thought; the aichat rollover option puts you in a fresh session, with the original session path injected, and you use sub agents to recover any arbitrary detail at any time. Now I keep auto-compact turned off and don’t compact ever.

https://github.com/pchalasani/claude-code-tools?tab=readme-o...

It’s a relatively simple idea; no elaborate “memory” artifacts, no discipline or system to follow, work until 95%+ context usage.

The tool (with the related plugins) makes it seamless: first type “>resume” in your session (this copies session id to clipboard), then quit and run

    aichat resume 

I added this to my local-LLM + Claude Code/ Codex-CLI guide here:

https://github.com/pchalasani/claude-code-tools/blob/main/do...

I don't know if others faced this issue; hopefully this is helpful, or maybe there are other fixes I'm not aware of.

This has enabled me to completely avoid compaction.

[1] https://github.com/pchalasani/claude-code-tools?tab=readme-o...

A skill that creates other skills can be very useful as well.

E.g. you could have:

- a set of skills to use design patterns of a library

- a skill to add to this skill-set -- either when prompted by user or autonomously via a stop-hook

E.g. I set up this combination for design patterns for the Langroid LLM-Agent framework:

https://github.com/pchalasani/claude-code-tools/tree/main/pl...

Amusingly, for a library [1] I’ve been building, 100% of the code is AI-written (with a huge number of iterations of course) and the ONLY part I wanted to write myself is the portion of the README that explains the thought process behind one of the features. It took a lot of thinking and iterations to come up with the right style and tone, and methodically explain the ideas in the right order.

Leaving that to an LLM would have been a frustrating exercise.

[1] https://github.com/pchalasani/claude-code-tools

It launches a TUI, offering a few ways to continue your work:

- blind trim - clones the session, truncates large tool calls/results and older assistant messages, which can clear up as much as 50% of context depending of course on what's going on; this is a quick hack to continue your work a bit longer

- smart trim - similar but uses headless agent to decide what to truncate

- rollover: the one I use most frequently; it creates a new session S1, and injects back-pointers to the parent session JSONL file of S, the parent's parent , and so on (what I call session lineage) , into the first user message, and the user can then prompt the agent to use a sub-agent to extract arbitrary context from the ancestor sessions to continue the work. E.g. you can, "Use sub-agent(s) to extract context from the last session shown in the lineage, about how we were working on fixing the tmux-cli issues". The repo has an aichat plugin that provides various slash commands, skills and agents, e.g. /recover-context can be used to extract context relevant to the last task in the parent session.

There is also an "aichat search" command that launches a Rust/Tantivy-based super-fast full-text search TUI to help find past work across Claude-Code/Codex-CLI sessions. (Note that claude --resume only searches session titles/names).

The search command has an agent-friendly JSONL mode for the agent/sub-agents to search for arbitrary past work across all sessions and query/filter with "jq" etc. This lets you open a fresh session and ask it recover context about your past work on X.

[1] https://github.com/pchalasani/claude-code-tools?tab=readme-o...

Installation:

    # Python package

For a quick start with great customizations, check out this popular config: gpakosz/.tmux

repo: https://github.com/gpakosz/.tmux.git

No I didn't condigure any of it and I"m using oh my tmux conf.

Oh my tmux! requires tmux 2.4+ and I would like to figure out what's oldest version of tmux people are actively using.

Here's a good source for more in-depth tuning .tmux.conf

Looks like no one has mentioned https://github.com/gpakosz/.tmux

You still need to learn the basics but this lowers the learning curve a lot.

Totally! Lately (this last year or so) i am also using this on top of tmux https://github.com/gpakosz/.tmux I don't knmow if you know it, its very close to the old configuration I worte myself, but with more colors :P

To get started with a decent tmux setup, start here: https://github.com/gpakosz/.tmux