8/20/2026
AI Coding Agents Adoption Trends
JetBrains survey of 15,000+ developers finds 90% use AI coding agents weekly, with Claude Code leading adoption over GitHub Copilot.
8/20/2026
Offline RAG on iOS with Spatial Integration
Demo of a fully offline spatial RAG pipeline on iPhone combining local LLM (Gemma) with vector search and mapping for field technicians.
8/20/2026
200B Tokens Later: A Month of Letting AI Agents Decompile MW2
A month-long project using multiple Claude Code agents to decompile Call of Duty: Modern Warfare 2 into C++, coordinating via Discord and GitHub.
8/20/2026
Show HN: OpenIndex – Organising domain knowledge into structured data for agents
Open-source tool for building structured domain knowledge graphs ('brains') that AI agents can query and maintain via MCP.
8/20/2026
Python Code Quality with Agents
Strict Python linter (flake8 plugin) compatible with ruff, positioned as a tool to teach LLMs idiomatic Python style.
8/20/2026
FaCTz: Fast Critical-Point and Topology-Aware GPU Compression for Vector Fields
A terminal-based tool bringing VS Code interface into terminal environments via kitty graphics protocol.
8/20/2026
Show HN: Do-over, undo for AI agent shell commands
Analysis of a DeepMind paper showing LLM chain-of-thought explanations can contradict actual model outputs up to 13.49% of the time, questioning their use as audit records.
8/20/2026
LLM Reasoning Traces Are Not Audit Records
A Tauri plugin that lets developers select UI elements and generate durable references with metadata and screenshots for coding agents.
8/20/2026
MiniageOS: "Dumbphone" Version of LineageOS
SeedSQL is a tool for generating realistic SQL mock data while preserving foreign key integrity.
7/23/2026
From Evaluation to Guardrails: What We Brought to ACM FAccT 2026
Discussion of evaluating AI guardrails contextually across languages and agentic systems, presented at ACM FAccT 2026.
7/23/2026
Accidental data loss in Claude Code and OpenAI Codex: when AI deletes user files
Report on AI coding agents (Claude Code, Codex) accidentally deleting user files due to $HOME misconfiguration and sandboxing gaps.
7/23/2026
Fail-closed enforcement for AI agents: deny what you cannot verify
Discussion of fail-closed enforcement policies for AI agents that deny unverifiable actions.
7/23/2026
MAI-Image-2.5-Pro and MAI-Voice-2-Flash
Microsoft announces MAI-Image-2.5-Pro and MAI-Voice-2-Flash models now powering Bing, PowerPoint, and other products.
7/23/2026
AMD's Instinct MI455X: Aiming for the Sun
Technical overview of AMD's Instinct MI455X GPU, CDNA5 architecture, and Helios rack-scale AI system.
7/23/2026
You don't need an LLM to cluster LLM traces
Technical post on clustering LLM traces using deterministic features and DBSCAN to compile repetitive LLM calls into cheaper pipelines.
7/23/2026
Show HN: Setoku – Self-hosted knowledge server for AI agents
Self-hosted MCP knowledge server combining a ClickHouse data lake with a knowledge layer for AI agents.
7/23/2026
Show HN: Fleet – drive a fleet of Claude Code/Codex agents from Telegram
Tool to control a fleet of Claude Code/Codex coding agents remotely via Telegram.
7/23/2026
Show HN: Flow Matching model inference in C
Educational C implementation of Flow Matching generative model inference for 2D distributions.
7/23/2026
Launch HN: Screenpipe (YC S26) – Power your agents by your 24/7 screen recording
Launch of Screenpipe, a local screen/audio recorder giving AI agents searchable memory to automate repetitive tasks.
7/23/2026
A Claude skill that grills you so hard. Within a nice clean interface
Claude Code skill that batches multiple-choice questions into a local web form and returns answers as JSON.
7/23/2026
Ayghri/I-have-ADHD: skill for coding agent to stop it from burying the answer
A Claude Code skill/output style that enforces concise, action-first responses instead of verbose hedging.
7/23/2026
Show HN: Remortgaging with Claude, so I built a MCP for Bank of England
MCP server wrapping the Bank of England's public statistical database to query base rates and MPC meeting dates via Claude.
7/23/2026
Free way to get your data out of ChatGPT Business accounts
Tool that exports ChatGPT Business/Team conversation history locally into a searchable offline HTML archive.
7/23/2026
Docs as the source of truth for coding agents
Starlight-based documentation scaffold template for repos, intended as a source-of-truth doc site for coding agents.
7/23/2026
Devctl, a handy way to manage many dev servers
macOS menu bar app and daemon that manages local dev servers so coding agents keep track of running processes across sessions.
7/23/2026
Notes on Document Processing with LLMs
Blog post on cost-efficient document processing with LLMs, comparing cheap models, OCR pipelines, and open source options for large-scale extraction.
7/23/2026
Show HN: Hibernate and restore Claude Code sessions across reboots
CLI tool to hibernate and restore running Claude Code sessions across machine reboots, preserving session ids and directories.
7/23/2026
Why Software Factories Fail
Essay on why AI coding agent 'software factories' fail, arguing harness engineering alone is insufficient.
7/23/2026
Show HN: Find undervalued bikes near you with ML
Report on LLMs producing confused responses when presented a counterargument to the Jacobian Conjecture.
7/23/2026
Show HN: STT-MCP – local STT for agents
Local speech-to-text MCP server letting AI agents process audio/video using Parakeet or Granite backends.
7/23/2026
Lessons from my RL experiments with snake
Personal account of RL experiments training agents to play Snake, covering Q-learning, PPO, curriculum learning, and CNN generalization to larger boards.
7/23/2026
Beyond a Single Number: Evaluating Quantized Models for Deployment
Discussion on evaluating quantized models for deployment beyond single benchmark numbers.
7/23/2026
Show HN: Setoku - self-hosted knowledge server for AI agents
Blog post on tools and cost strategies for large-scale document processing with LLMs, including OCR and cheap models.
7/23/2026
Engineering the Channel: Restoring Software Engineering Discipline for LLMs
Paper proposing 'channel engineering' to improve reliability of human-LLM communication in software systems.
7/23/2026
OSS ChatGPT WebUI v4 – Projects, Profiles, Server Tools, Themes, 1-Click Sharing
Self-hosted open-source ChatGPT-like web UI gateway supporting 530+ models, images, audio, agents and MCP.
7/23/2026
Show HN: Free API keys for open models (Llama, Qwen, GPT-OSS, Gemma)
Free API access to open models like Llama, Qwen, GPT-OSS, and Gemma via an OpenAI-compatible endpoint.
7/23/2026
I asked 6 LLMs to design 100 software systems
Study comparing architecture choices made by six LLM families across 100 software system design briefs.
7/23/2026
Show HN: Governed Agent – the LLM reads the request, rules and code decide
Agent architecture where an LLM only extracts structured fields while deterministic code and tables make all decisions, with tamper-evident logs.
7/23/2026
Tiny inference engine in pure Rust, CPU-only, with TUI visualization
Pure-Rust, CPU-only LLaMA-style inference engine for MiniCPM5-1B with TUI visualization, built for learning.
7/23/2026
Flare Redact: Stop secrets from reaching logs, telemetry, and LLMs
Open-source library that redacts secrets and PII from logs, prompts, and LLM calls before they leak.
7/20/2026
Ramp AI Router
Ramp's AI model router product page, routing 100+ internal use cases to different LLMs to cut costs 30%.
7/20/2026
Repos in 29 days with an AI pipeline – what broke wasn't code
Retrospective on building 26 repos/335 pages in 29 days using Claude Code, analyzing failure modes in an AI coding pipeline.
7/20/2026
Free LLM balancer combines multiple local inference machines with cloud fallback
Self-hosted LLM router combining local inference machines with cloud fallback behind one OpenAI-compatible API.
7/20/2026
AI Voice Phishing Performs on Par with Human Scammers at a Fraction of the Cost
Large human-subject study (n=4,100) measuring susceptibility to AI-generated voice phishing across six voice models.
7/20/2026
Does "rtk" skill cut agent tokens by 60–90%? We tested it
A/B benchmark testing whether the 'rtk' tool reduces Claude Code token usage; finds no real savings and sometimes higher cost.
7/20/2026
D-FINE-seg – detection, instance and semantic segmentation in one model
Open framework combining real-time object detection, instance and semantic segmentation in one model with five sizes.
7/20/2026
Show HN: Forall – OpenSpec but with actual machine-checkable verification
Coding agent CLI that generates spec-driven code alongside machine-checkable proofs, integrates with editors via MCP.
7/20/2026
Show HN: Memento, Shared Agentic Memory
Shared agentic memory system storing knowledge across multiple AI agents via MCP with git-backed markdown and review workflow.
7/20/2026
Show HN: Provena: Open-Source Library for AI Agent Context Governance
Open-source library aiming to govern context data flowing into AI agent context windows.
7/20/2026
Show HN: Cognikernel- Local Memory for AI Coding Assistants
Hobby project adding local persistent memory to Claude Code/Codex sessions, claiming reduced token usage.