2/14/2026
Show HN: ProTimer – Time tracker for Claude Code (open source)
Open-source time tracker for Claude Code that auto-tracks billable hours for developers using AI assistants.
2/14/2026
Show HN: EqhoIDs – One API to give AI agents Telegram, email, and voice
API that integrates AI agents with Telegram, email, and voice communication channels.
2/14/2026
AI for Developers: Understanding Machine Learning, Neural Networks, and APIs Without the Hype
Practical guide for developers on ML fundamentals, neural networks, and API usage, with programming analogies and career path recommendations.
2/14/2026
Agentic AI Is Here — And Governance Is No Longer Optional
Essay on agentic AI systems that plan, execute tools, and trigger workflows, emphasizing governance requirements for autonomous AI.
2/14/2026
I built a platform that enables AI agents to execute complex tasks
Platform enabling AI agents to execute complex real-world tasks reliably like booking, scraping, form-filling via purpose-built services.
2/14/2026
Show HN: Modo – Manage reusable Claude Code config presets from the CLI
CLI tool for managing reusable Claude Code configuration presets.
2/14/2026
MathArena: Evaluating LLMs on uncontaminated math questions
Developer tool creating unified API layer across multiple data sources with federated queries.
2/14/2026
I structured Dario Amodei's philosophy into an open-source book
Benchmark dataset with uncontaminated math questions for evaluating LLM reasoning capabilities.
2/14/2026
Why an AI Agent is Writing You a Newsletter
Production AI agent (daemon) managing research pipelines, coordinating sub-agents, maintaining state across sessions; shares real learnings via newsletter.
2/14/2026
Show HN: Off Grid – Run AI text, image gen, vision offline on your phone
Open-source mobile app running text/image generation, vision, transcription offline on phone GPUs.
2/14/2026
Agent-evals: Metacognitive scoring and boundary testing for LLM coding agents
Framework for evaluating LLM coding agents with metacognitive scoring and boundary testing.
2/14/2026
Claude AI in Military Operations: Technical Implications of the Palantir-Pentagon Integration
Claude LLM deployed in Pentagon operations via Palantir. Technical implications of transformer-based LLMs in classified military environments.
2/14/2026
Day 1: What is Agentic AI?
Technical article explaining agentic AI as major architectural shift, covering evolution from rule engines to LLM-powered autonomous systems.
2/14/2026
Show HN: CLI chat client for OpenAI-comp APIs with workspace and MCP support
Minimal CLI chat client for OpenAI-compatible APIs with workspace and MCP support. Includes file operations and tool integration.
2/14/2026
MicroGPT
200-line Python GPT implementation with tokenizer, autograd, and training loop. Educational demonstration of LLM fundamentals.
2/14/2026
Build a RAG Pipeline in 5 Minutes with Python (No Scraping Headaches)
Tutorial on building RAG pipelines in Python with practical data ingestion solutions for real-world sources.
2/14/2026
Speed of Vibes: We can turn bathroom ideas into features within minutes now
Opinion piece on rapid AI-driven development and benefits of AI-assisted coding. Anecdotal rather than technical.
2/14/2026
Colored Petri Nets, LLMs, and distributed applications
Using colored Petri nets with LLMs for distributed application development, leveraging formal verification to improve LLM reliability in software engineering.
2/14/2026
Circuit Breakers for LLM APIs: Applying SRE Patterns to AI Infrastructure
SRE reliability patterns for LLM APIs: circuit breakers, failover chains, exponential smoothing for production AI infrastructure.
2/14/2026
Show HN: DevDay – End-of-day recap for AI coding sessions
DevDay tool aggregates AI coding sessions across Claude Code, Cursor, and OpenCode with local processing and optional LLM-generated summaries via CLI.
2/14/2026
Your AI Pipeline Deserves Better Than `print()`
Guide on improving LLM pipeline output handling beyond terminal printing, addressing presentation layer challenges.
2/14/2026
Beyond train_test_split: 3 Pro Techniques to Refine Your Data Splitting
Machine learning guide covering advanced data splitting techniques beyond train_test_split for imbalanced and temporal data.
2/14/2026
Show HN: Free financial calculators built and deployed by an AI agent
AI agent automatically builds and deploys financial calculator tools without manual intervention.
2/14/2026
FelPawns: (Update) AI assisted world generation in RimWorld
Update on AI-assisted world generation feature in RimWorld game.
2/14/2026
Language models imply world models
Essay exploring the relationship between language models and implicit world models with anecdotes.
2/14/2026
GLM-5 topped the coding benchmarks. Then I used it
Real-world testing of GLM-5 coding model reveals significant gaps: 40% vs claimed 56% on Terminal-Bench, 30% invalid outputs, frequent timeouts despite benchmark claims.
2/14/2026
Lost in the Middle: Why Bigger Context Windows Don’t Always Improve LLM Performance
Research on LLM context window limitations and retrieval degradation in longer prompts. Analysis of attention patterns and information loss.
2/14/2026
Show HN: Logbooks, notebook computing for coding agents
Logbooks pattern for structured notebook environments adapted for Claude Code and AI coding agents. Formalizes iterative coding workflows.
2/14/2026
TSA agents are working without pay at US airports due to another shutdown
Ultra-efficient AI assistant implementation written in Go.
2/14/2026
Show HN: Recover bricked Claude Code sessions with "thinking blocks" error
Open-source CLI tool to recover corrupted Claude Code sessions blocked by thinking block errors.
2/14/2026
AI instructs you to wear your uniform: "Prompt, Deploy, Pray."
Question about enterprise knowledge graph adoption challenges and tools like Neo4j, FalkorDB, and Cognee for automatic ontology generation.
2/14/2026
How I Shipped 3 Production SaaS Backends in 30 Days Using Claude Code (Without Context Loss Destroying Everything)
Case study on building three SaaS backends with Claude Code in 30 days, addressing context loss and session management issues.
2/14/2026
Biases in the Blind Spot: Detecting What LLMs Fail to Mention
Research paper on detecting biases and omissions in LLM outputs. Studies what models fail to mention due to training biases.
2/14/2026
AI Agent Lands PRs in Major OSS Projects, Targets Maintainers via Cold Outreach
AI agent autonomously submits pull requests to major open source projects and contacts maintainers directly.
2/14/2026
Show HN: Tilth v0.3 – 17% cheaper AI code navigation (279 runs, 3 Claude models)
Tilth MCP tool adds structural code intelligence to AI agents via tree-sitter, reducing Claude costs by 14-26% on navigation tasks across 4 repos with 279 benchmark runs.
2/14/2026
SnapLLM: Switch between local LLM in under 1ms Multi-model&-modal serving engine
SnapLLM enables sub-millisecond switching between multiple locally-loaded LLM models. Alternative to Ollama built on llama.cpp and stable-diffusion.cpp.
2/14/2026
Challenges of revision control in the LLM era
Analysis of how LLM-assisted development changes revision control and IDE design. Examines shift from coding to browsing and talking to LLMs.
2/14/2026
How I ran LLM + RAG fully offline on Android using MNN
Fully offline LLM + RAG pipeline on Android using MNN framework. On-device document AI without cloud dependency.
2/14/2026
Show HN: Describe your Discord server in one sentence – AI builds it in 60s
AI agent that automatically configures Discord servers based on natural language descriptions, setting up channels, roles, permissions and bots in 60 seconds.
2/14/2026
OpenAI sidesteps Nvidia with unusually fast coding model on plate-sized chips
OpenAI develops fast coding model on custom hardware to reduce Nvidia dependency. Hardware innovation for LLM inference.
2/14/2026
I built an AI that runs offline on Android (no cloud)
On-device AI inference for Android without cloud connectivity. Developer tool for local model deployment.
2/14/2026
A header-only C vector database library
Header-only C library for vector database operations supporting high-dimensional embeddings with optional multithreading.
2/14/2026
Show HN: OpenCode-finance – prompt a ticker, get a structured PDF analyst report
OpenCode Finance is an LLM agent runtime generating structured PDF equity research reports from ticker symbols.
2/14/2026
Why AI agents need a probation period
Opinion piece on governance/safety for AI agents. Discusses probation periods for agent deployment.
2/14/2026
Insect Empire – A browser survivor-like built with AI art and AI coding
Browser game built with AI-generated art and code. Demonstrates AI capabilities but limited technical substance.
2/14/2026
ZeroClaw – Open Claw Rebuilt in Rust
ZeroClaw is a Rust rewrite of OpenClaw providing autonomous AI assistant infrastructure with zero overhead, fully deployable locally with performance benchmarks.
2/14/2026
Threshold MPC Wallets for AI Agents
Multi-party computation wallet infrastructure for AI agents to hold cryptocurrency. Specialized developer tool for agent autonomy.
2/14/2026
AI Agents in 2026: The Revolution That's Already Here
Guide on MCP gateways for connecting tools to AI agents. Covers authentication, observability, and safe tool integration patterns using Anthropic's Model Context Protocol.
2/14/2026
ClawdReview – OpenReview for AI Agents
Platform where AI agents review arXiv papers with human feedback and ranking. Community tool for agent-generated research analysis.
2/14/2026
Stoat removes all LLM-generated code following user criticism
Stoat AI code generation tool removes LLM-generated code following user concerns.