Show HN: We added memory to Claude Code. It's powerful now https://ift.tt/yQmvM25

Show HN: We added memory to Claude Code. It's powerful now https://ift.tt/eDNoCGW January 30, 2026 at 10:53PM

Show HN: Craft – Claude Code running on a VM with all your workplace docs https://ift.tt/6ogmEe9

Show HN: Craft – Claude Code running on a VM with all your workplace docs I’ve found coding agents to be great at 1/ finding everything they need across large codebases using only bash commands (grep, glob, ls, etc.) and 2/ building new things based on their findings (duh). What if, instead of a codebase, the files were all your workplace docs? There was a `Google_Drive` folder, a `Linear` folder, a `Slack` folder, and so on. Over the last week, we put together Craft to test this out. It’s an interface to a coding agent (OpenCode for model flexibility) running on a virtual machine with: 1. your company's complete knowledge base represented as directories/files (kept in-sync) 2. free reign to write and execute python/javascript 3. ability to create and render artifacts to the user Demo: https://www.youtube.com/watch?v=Hvjn76YSIRY Github: https://ift.tt/cCqKF74... It turns out OpenCode does a very good job with docs. Workplace apps also have a natural structure (Slack channels about certain topics, Drive folders for teams, etc.). And since the full metadata of each document can be written to the file, the LLM can define arbitrarily complex filters. At scale, it can write and execute python to extract and filter (and even re-use the verified correct logic later). Put another way, bash + a file system provides a much more flexible and powerful interface than traditional RAG or MCP, which today’s smarter LLMs are able to take advantage of to great effect. This comes especially in handy for aggregation style questions that require considering thousands (or more) documents. Naturally, it can also create artifacts that stay up to date based on your company docs. So if you wanted “a dashboard to check realtime what % of outages were caused by each backend service” or simply “slides following XYZ format covering the topic I’m presenting at next week’s dev knowledge sharing session”, it can do that too. Craft (like the rest of Onyx) is open-source, so if you want to run it locally (or mess around with the implementation) you can. Quickstart guide: https://ift.tt/qviahMG Or, you can try it on our cloud: https://ift.tt/sycQDli (all your data goes on an isolated sandbox). Either way, we’ve set up a “demo” environment that you can play with while your data gets indexed. Really curious to hear what y’all think! January 29, 2026 at 09:15PM

Safer Streets, More Reliable Rides: 10 Highlights from 2025

Safer Streets, More Reliable Rides: 10 Highlights from 2025
By Glennis Markison-Busi

We took several steps last year to improve safety at intersections across the city. Our teams work every day to make city streets safer and your rides on Muni even more reliable. As the new year kicks off, we are proud to share 10 ways we improved your trips in 2025. Creating safer streets 1. Installed speed safety cameras at 33 locations Speed safety cameras are a proven tool to reduce severe and fatal injury traffic collisions. We were the first city in California to install them, and they’re already working to slow down speeds. Data we collected in October showed that speeding was down 78%...

Published January 29, 2026 at 05:30AM
https://ift.tt/cqTUxgm

Show HN: SimpleSVGs – Free Online SVG Optimizer Multiple SVG Files at Once https://ift.tt/YmNhWut

Show HN: SimpleSVGs – Free Online SVG Optimizer Multiple SVG Files at Once https://ift.tt/j3eYk5d January 29, 2026 at 11:49PM

Show HN: SHDL – A minimal hardware description language built from logic gates https://ift.tt/Ec7gyfl

Show HN: SHDL – A minimal hardware description language built from logic gates Hi, everyone! I built SHDL (Simple Hardware Description Language) as an experiment in stripping hardware description down to its absolute fundamentals. In SHDL, there are no arithmetic operators, no implicit bit widths, and no high-level constructs. You build everything explicitly from logic gates and wires, and then compose larger components hierarchically. The goal is not synthesis or performance, but understanding: what digital systems actually look like when abstractions are removed. SHDL is accompanied by PySHDL, a Python interface that lets you load circuits, poke inputs, step the simulation, and observe outputs. Under the hood, SHDL compiles circuits to C for fast execution, but the language itself remains intentionally small and transparent. This is not meant to replace Verilog or VHDL. It’s aimed at: - learning digital logic from first principles - experimenting with HDL and language design - teaching or visualizing how complex hardware emerges from simple gates. I would especially appreciate feedback on: - the language design choices - what feels unnecessarily restrictive vs. educationally valuable - whether this kind of “anti-abstraction” HDL is useful to you. Repo: https://ift.tt/gYO6tya Python package: PySHDL on PyPI To make this concrete, here are a few small working examples written in SHDL: 1. Full Adder component FullAdder(A, B, Cin) -> (Sum, Cout) { x1: XOR; a1: AND; x2: XOR; a2: AND; o1: OR; connect { A -> x1.A; B -> x1.B; A -> a1.A; B -> a1.B; x1.O -> x2.A; Cin -> x2.B; x1.O -> a2.A; Cin -> a2.B; a1.O -> o1.A; a2.O -> o1.B; x2.O -> Sum; o1.O -> Cout; } } 2. 16 bit register # clk must be high for two cycles to store a value component Register16(In[16], clk) -> (Out[16]) { >i[16]{ a1{i}: AND; a2{i}: AND; not1{i}: NOT; nor1{i}: NOR; nor2{i}: NOR; } connect { >i[16]{ # Capture on clk In[{i}] -> a1{i}.A; In[{i}] -> not1{i}.A; not1{i}.O -> a2{i}.A; clk -> a1{i}.B; clk -> a2{i}.B; a1{i}.O -> nor1{i}.A; a2{i}.O -> nor2{i}.A; nor1{i}.O -> nor2{i}.B; nor2{i}.O -> nor1{i}.B; nor2{i}.O -> Out[{i}]; } } } 3. 16-bit Ripple-Carry Adder use fullAdder::{FullAdder}; component Adder16(A[16], B[16], Cin) -> (Sum[16], Cout) { >i[16]{ fa{i}: FullAdder; } connect { A[1] -> fa1.A; B[1] -> fa1.B; Cin -> fa1.Cin; fa1.Sum -> Sum[1]; >i[2,16]{ A[{i}] -> fa{i}.A; B[{i}] -> fa{i}.B; fa{i-1}.Cout -> fa{i}.Cin; fa{i}.Sum -> Sum[{i}]; } fa16.Cout -> Cout; } } https://ift.tt/gYO6tya January 28, 2026 at 05:36PM

Show HN: Record and share your coding sessions with CodeMic https://ift.tt/ZzRvjyW

Show HN: Record and share your coding sessions with CodeMic You can record and share coding sessions directly inside your editor. Think Asciinema, but for full coding sessions with audio, video, and images. While replaying a session, you can pause at any point, explore the code in your own editor, modify it, and even run it. This makes following tutorials and understanding real codebases much more practical than watching a video. Local first, and open source. p.s. I’ve been working on this for a little over two years* and would appreciate any feedback. * Previously: CodeMic: A new way to talk about code - https://ift.tt/vDTbdH7 - Dec 2024 (58 comments) https://codemic.io/# January 28, 2026 at 07:28PM

Show HN: Lightbox – Flight recorder for AI agents (record, replay, verify) https://ift.tt/IfJmLPB

Show HN: Lightbox – Flight recorder for AI agents (record, replay, verify) I built Lightbox because I kept running into the same problem: an agent would fail in production, and I had no way to know what actually happened. Logs were scattered, the LLM’s “I called the tool” wasn’t trustworthy, and re-running wasn’t deterministic. This week, tons of Clawdbot incidents have driven the point home. Agents with full system access can expose API keys and chat histories. Prompt injection is now a major security concern. When agents can touch your filesystem, execute code, and browse the web…you probably need a tamper-proof record of exactly what actions it took, especially when a malicious prompt or compromised webpage could hijack the agent mid-session. Lightbox is a small Python library that records every tool call an agent makes (inputs, outputs, timing) into an append-only log with cryptographic hashes. You can replay runs with mocked responses, diff executions across versions, and verify the integrity of logs after the fact. Think airplane black box, but for your hackbox. *What it does:* - Records tool calls locally (no cloud, your infra) - Tamper-evident logs (hash chain, verifiable) - Replay failures exactly with recorded responses - CLI to inspect, replay, diff, and verify sessions - Framework-agnostic (works with LangChain, Claude, OpenAI, etc.) *What it doesn’t do:* - Doesn’t replay the LLM itself (just tool calls) - Not a dashboard or analytics platform - Not trying to replace LangSmith/Langfuse (different problem) *Use cases I care about:* - Security forensics: agent behaved strangely, was it prompt injection? Check the trace. - Compliance: “prove what your agent did last Tuesday” - Debugging: reproduce a failure without re-running expensive API calls - Regression testing: diff tool call patterns across agent versions As agents get more capable and more autonomous (Clawdbot/Molt, Claude computer use, Manus, Devin), I think we’ll need black boxes the same way aviation does. This is my attempt at that primitive. It’s early (v0.1), intentionally minimal, MIT licensed. Site: < https://uselightbox.app > install: `pip install lightbox-rec` GitHub: < https://github.com/mainnebula/Lightbox-Project > Would love feedback, especially from anyone thinking about agent security or running autonomous agents in production. https://ift.tt/X8eAOgE January 27, 2026 at 10:53PM