Comments URL: https://news.ycombinator.com/item?id=49368141

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49187082

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49175149

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48618332

Points: 5

# Comments: 0

harbor up omlx opencode

Slop is no fun to deal with, so we have a thesis that slop should be left for agents to read and human-to-human communication should happen outside of passing empty fluffy docs to one another. To realise that, we have a workspace with group chats where multiple agents and humans can work together and agents can engage with humans for additional information when needed. The challenge is, of course, to find the right level of autonomy for the agents and let the agent learn and follow user's workflows well enough to be useful.

Comments URL: https://news.ycombinator.com/item?id=48280543

Points: 4

# Comments: 0

This is just a fun side project, but it is still a fully functional agent with read-only access to your system (no web tools, to avoid exfill). It can explore whatever folder you start it in and then answer you yes or no for your question: "Is code ready for release?", "Read my notes, should I buy a GPU?", or some less useful ones, of course.

Built with Bun/OpenTUI.

Comments URL: https://news.ycombinator.com/item?id=48280124

Points: 1

# Comments: 0

Bun+OpenTUI for CLI, separate Rust binary for indexing the sessions of your coding agents. Release video made with Hyperframes.

Comments URL: https://news.ycombinator.com/item?id=48172681

Points: 1

# Comments: 1

mi Works with any OpenAI-compatible model (including local ones). Has REPL, skills, and recursive agents and only 30 lines of code, optimised for local models.

--- mi --sandbox -p 'fix tests until all are passing' ---

Comments URL: https://news.ycombinator.com/item?id=48120924

Points: 1

# Comments: 0

``` harbor pull unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_XL

# Open WebUI -> llama.cpp + SearXNG for Web RAG + OpenTerminal as sandbox harbor up searxng webui llamacpp openterminal ```

That's it, it's already better than Claude's or ChatGPT's app.

Comments URL: https://news.ycombinator.com/item?id=48070211

Points: 2

# Comments: 0

Spec is essentially a set of facts + fluff. List of facts is essentially the spec minus the fluff. This was my main idea when trying this approach out. It worked quite well, so I went on building the CLI and a set of skills to better guide the agent about this specific workflow.

Outside of that, I found a few things particularly useful so far: - I can seed a relatively complex project with just a few core assumptions about behaviors I have, agent will firgure out all the gaps in a formalised way - I can easily diff/compare the fact sheets against one another. One example: I built a fact sheet for a fairly hairy Python CLI, then asked the agent to update all Python-related entries to their Rust equivalents, then rebuilt this CLI in Rust in the scope of another project - It's much quicker than working with large spec formats, agent uses less tool calls to capture the context it needs to work on something - After doing large refactoring, agent doing a "fact check" is essentially a full on e2e test run

Two biggest gains for agentic use are because fact sheets are more compact and that they are all assertions about the desired state, it's much easier to reason about things that should and shouldn't be there

In the end every spec is just a bunch of facts, so I decided to leave that and throw away everything else while making it friendlier for agentic use.

Introducing facts - skills and CLI for agents to use facts-driven development. https://github.com/av/facts

Comments URL: https://news.ycombinator.com/item?id=48008906

Points: 7

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=47990330

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47933602

Points: 6

# Comments: 0

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.