I made Claude Managed Agents for all harnesses and models
Developer created Claude Managed Agents compatible with multiple harnesses and models for extensible agent deployment.
Developer created Claude Managed Agents compatible with multiple harnesses and models for extensible agent deployment.
Zero-human company stack in Go: single-binary jira-like PM system where AI agents autonomously take tasks, delegate, and ship code.
NoxScan: port and vulnerability scanner using LLM for false-positive filtering, reduces manual triage of security scan results.
Otel-GUI: lightweight open source OpenTelemetry viewer for local development and debugging, simpler alternative to heavyweight existing solutions.
Fragment about Google's AI avatar feature on YouTube Shorts.
Software tool using LLMs to auto-populate security review documents from company policies.
Framework for enhancing AI agent memory systems using persistent storage, enabling stateful agent behavior across sessions.
Vibetime is a tool for tracking productivity metrics and code generation output during AI-assisted coding sessions.
Junco is a local 9MB coding agent for macOS using Apple Intelligence API, demonstrating on-device LLM agent capabilities.
CLI tool for image generation and editing using Google Gemini models, built while working with coding agents.
Go SDK for LLM applications supporting 22+ providers with MCP support, 2 core dependencies, faster streaming and cold starts than Vercel AI SDK.
EVE: C++20 SIMD library research project providing type-based wrappers around SIMD extensions for high-performance computing.
Technical analysis showing same LLM models exhibit different performance characteristics across different API providers.
Index is an API directory for AI agents with payment protocol support, MCP server integration, and real-time health checks.
Self-hosted music listening stats visualization tool for Navidrome users showing top songs, artists, and listening patterns.
Educational article on systematic selection and application of agentic AI design patterns for building reliable, scalable agent systems.
Memory Sync tool syncs a single Memory.md file across multiple AI chat tools to maintain consistent long-term context and preferences.
Article on hidden costs of AI code generation: engineers spending time auditing machine output instead of building, affecting retention and code quality.
Open-source web app using Rails and NVIDIA garak for security vulnerability scanning of LLM chatbots before deployment.
HN discussion asking for open source tools combining AI code generation with deployment capabilities.
Recure is an AI-powered dataset discovery tool with semantic search and automated scanning across multiple data sources for ML teams.
QVAC SDK: open-source JavaScript/TypeScript SDK for building local-first AI applications on desktop and mobile.
AI-powered data analysis tools embedded in codebases help PMs and analysts explore unfamiliar SQL/data structures interactively.
Analysis of AI's actual impact: replaces specific capabilities (coding, testing, docs), not headcount; managing complexity remains.
Relvy (YC F24): AI agent for automating on-call runbooks, analyzes telemetry and code to debug production issues.
Dirac: open-source AI coding agent with hash-anchored AST, 64.8% cheaper than competitors; includes comparative evals on 8 tasks.
WebGPU physics prototype implementing Augmented Vertex Block Descent algorithm for rigid/soft-body simulation.
Bash tool for quick switching between Claude Code accounts with secure Keychain credential storage.
Formal reasoning engine for LLM coding assistants to improve code analysis and transitive reasoning beyond ad-hoc grepping.
Historical timeline of Atari 8-bit computers from 1979-1992 with pricing analysis.
CSS Studio: browser-based design tool that uses AI agents to edit codebases via MCP server and Claude Channels; streams CSS changes as JSON.
Discussion of production AI systems with unexplained failures despite passing metrics; explores trust issues with model behavior and verification.
Discussion on whether non-coders can build high-tech products like agent platforms and no-code tools using modern LLM tools.
HN discussion asking if a rollout tool for customized Gemini action flows targeted to user groups would be useful for managers.
Developer discusses having 7 years of private work experience with no public GitHub profile due to NDAs and proprietary work.
Guide for efficiently navigating Hong Kong Disneyland and riding all attractions with minimal waiting.
Commercial tool for removing image backgrounds using AI. Ecommerce-focused product.
Open source Obsidian plugin integrating Claude Code and other AI agents into note-taking workflow.
Lenny's Memory library for building context graphs to improve AI agent performance and memory.
Academic paper on GPU Rowhammer privilege escalation attacks. Security research with code, not AI-focused.
Stockfish chess engine removes classical evaluation in favor of NNUE. Machine learning application but niche domain.
Kern framework for building collaborative AI agents. Agent development tooling.
1.7B parameter LLM running on Apple Watch. Edge AI/LLM application demonstration.
Fluent language learning kit using Claude Code with spaced repetition and adaptive tracking. LLM application.
Oracle announces 30k employee layoffs (18% of workforce) driven by AI infrastructure pivot.
Speculative opinion piece about future AI model monetization and economic impact. No technical content.
Discussion about removed 'buddy' feature from Claude Code v2.1.97. Opinion piece on developer tooling changes.
Linux release notes generated by AI from official documentation.
Technical notes on running llama.cpp LLM on TK1 device with various OS/tooling combinations. Edge deployment.
Afterchain protocol for post-mortem digital asset execution. Blockchain/cryptocurrency focused, not AI-related.