rtk-ai/rtk

Haven't benchmarked it, but for agentic coding e.g. Claude Code I found this useful: https://github.com/rtk-ai/rtk

I find grep and common cli command spam to be the primary issue. I enjoy Rust Token Killer https://github.com/rtk-ai/rtk , and agents know how to get around it when it truncates too hard.

I've found RTK CLI proxy [1] quite useful for reducing token usage [1]: https://github.com/rtk-ai/rtk/

I've been running https://github.com/rtk-ai/rtk for a week seems to be a good balance between culling out of context and not just killing everything. I've been running https://github.com/Opencode-DCP/opencode-dynamic-context-pruning in opencode as well. It seems more aggressive.

…follow (the exact number depends on the specific model so instructions that are fine for one model may overwhelm another). If this keeps happening, consider trimming your instructions or even better, solving it at the harness level (like intercepting and rewriting ripgrep calls to use your thing, like rtk [0] does in agents that supports this) Overall, never leave to an agent an instruction that must be followed at all times. For example, doing things in a git hook beats a multi-command workflow every time the agent commit, etc. Is this state of things forever? I don't think so. Very soon models will become so better this will be a non-problem [0] https://github.com/rtk-ai/rtk

I can see that and I don't know your setup, but there are people pushing >70t/s with MTP on a single 3090, with big contexts still >50t/s. 64k is not a lot for agentic coding, and IIRC 128k with turboquant and the likes should be possible for you. r/LocalLLM/ and r/LocalLLaMA/ are worth a visit IMO. EDIT: just found this recipe repo, may wanna give it a go: https://github.com/noonghunna/club-3090 EDIT-2: this can also shave off a lot of context need for tool calling -> https://github.com/rtk-ai/rtk

What about some thing like https://github.com/rtk-ai/rtk

To reduce token count on command outputs you can also use RTK [0] [0]: https://github.com/rtk-ai/rtk

Yeah, the change has been very noticeable imo. Did you already try tools that can help to reduce token usage cost so you can get more prompts in within your same plan? Some great ones are https://github.com/rtk-ai/rtk https://github.com/gglucass/headroom-desktop https://github.com/chopratejas/headroom https://github.com/samuelfaj/distill

I used to use Gemini CLI and was pretty happy with it… until I started using Claude Code. I think it’s, for now, the most advanced AI tool available right now. You can manage skills, the MCP, plugins, agents, hooks… It’s a truly comprehensive tool, but its main drawback is the token consumption of the Anthropic model, especially in recent days. There are solutions to reduce input tokens, for example this GitHub project https://github.com/rtk-ai/rtk . It uses hooks to replace certain commands with optimized ones and helps reduce the number of input tokens. It’s a start...

My criteria is "do they measure performance, or at least even try to?". Caveman [1], RTK [2] and more recently ponytail [3] don't or use a few trivial tests. Those projects don't measure performance on widely used benchmarks (like SWE Pro and stuff), that have their issues but at least it would give some indication. They also don't measure "big model + caveman vs smaller model". I've had a few times where removing all custom instructions that I started using with model N-2 made model N perform way better, so I'm very suspicious of everything that changes how the model works, it's easy to get degraded performance silently and suddenly you're paying latest Opus costs for 6 months old Sonnet p…

I was looking through the issues as investigation. Some issues that caught my attention are looking quite bad https://github.com/rtk-ai/rtk/issues/2494 https://github.com/rtk-ai/rtk/issues/2462 https://github.com/rtk-ai/rtk/issues/2395

Similar tools in the space: RTK which I guess is a close equivalent. https://github.com/rtk-ai/rtk Headroom which is complementary. https://github.com/chopratejas/headroom I have tried both of these and I have to say, I didn't notice any difference. That's not to say there wasn't a difference (rtk logs were telling me enthusiastically how many tokens I'd saved), it's just that pretty much all context is coming from reading data from files and neither of these tools can do anything about that. As I switched from Claude Code to Pi recently, and tweaked my workflow, I've seen a much bigger/more obvious reduction in context use from that and I don't use either of these tools right now. I'…

Faced this too. Tried https://github.com/rtk-ai/rtk to compress cli output but some commands started failing and the savings were minimal. Ended up just being more deliberate about context size instead of adding more tooling on top