Open-source TUI/CLI coding agent maintained by the SST team; runs in a terminal, supports 75+ LLM providers via Models.dev, and offers session sharing.
@hn_46b39f
27 days ago
I went on Kilo's website and it's seems to be closing doors on what I'm already doing. My coding is done with OpenCode with an OpenRouter API Key. Going with KiloCode would be doing the same, but with some more layers. And given that I can't see the on-demand API pricing, I'm really not convinced on how it would be an improvement.
@hn_c55035
about 1 month ago
I tried, really really hard but then I realised that I essence it's a poorly written agentic coding assistant that wastes a lot of tokens antropomorphising itself while forcing me to debug via WhatsApp instead of normal tools. So I leaned into that and made OpenCode my general assistant, it worked much better in this aspect.
@hn_2e63de
about 1 month ago
Interesting timing — I've been building on Cloudflare Workers with edge-first constraints, and the resource footprint of most AI coding tools is striking by comparison. A TypeScript agent that uses 1GB+ RAM for a TUI feels like the wrong abstraction. The edge computing model forces you to think differently about state, memory, and execution — maybe that's where lighter agentic tools will emerge.
@hn_3660a7
about 1 month ago
I tried to list the competing open-source AI coding agents to compare their popularity over time — opencode wins for now. https://www.star-history.com/?repos=anthropics%2Fclaude-code
@hn_e3d777
about 2 months ago
owning GGUF conversion step is good in sone circumstances, but running in fp16 is below optimal for this hardware due to low-ish bandwidth. It looks like context is set to 32k which is the bare minimum needed for OpenCode with its ~10k initial system prompt. So overall, something like Unsloth's UD q8 XL or q6 XL quants free up a lot of memory and bandwidth moving into the next tier of usefulness.