Absurd: Simplest durable execution workflow system
Absurd is a durable execution workflow system built entirely on Postgres, handling scheduling and retries without additional services.
Absurd is a durable execution workflow system built entirely on Postgres, handling scheduling and retries without additional services.
Analysis of zooming UI paradigms in web interfaces, comparing Prezi and impress.js with a new alternative approach.
Tutorial on building an AI companion with memory using OpenAI GPT-4o and CortexDB to create stateful assistant experiences.
Article about counterfeit Apple Watches revealed through CT scans, comparing fake and original designs.
Skill for AI coding agents that analyzes session transcripts to identify friction and suggest improvements, currently supporting Claude Code with roadmap for other agents.
Orca framework: deterministic execution engine for composable AI agent skills with DAG workflows, safety gates, and 122 built-in Python capabilities following open standard.
Case study of using AI tools to add 10,000 historic photos to OldNYC with improved geocoding and reduced infrastructure costs via OpenStreetMap.
Open-source project management tool for tracking multiple AI-generated projects with completion metrics, health signals, and code-aware insights.
Tool replacing Claude Code's context stuffing with semantic search using tree-sitter parsing and vector embeddings stored on Git branches for team collaboration.
Commentary on Cadence's ChipStack AI for chip design and criticism of LLM agents designing hardware with potential hallucinations.
GhostVM: tool providing isolated macOS workspaces for AI agents with data control, deep host integration, clipboard/file sharing, and permission management.
Library for centralizing and versioning AI agent skills across projects with automatic syncing, MCP discovery support, and version management.
Video titled about building AI agents on infrastructure that may become obsolete in 18 months.
Open-source evaluation tool for structured LLM outputs with schema validation, failure taxonomy, and dataset comparison beyond binary pass/fail metrics.
Personal essay about using AI with a persistent memory system called CORTEX, reflecting on AI limitations through the genie parable.
LiveKit integration with Telnyx infrastructure for hosting voice AI agents with 50% cost reduction and low-latency STT/TTS.
Personal blog post about startup founder experiences and product-market fit challenges.
Philosophical essay exploring what it means for language models to have subjective experience, building on Nagel's 'What is it like to be a bat?'
iOS dictation app using AI to clean speech-to-text output by removing filler words and editing transcriptions.
Emacs package providing native Codex IDE integration with MCP bridge support for direct editor context access.
Vajra is a background coding agent that polls Linear issues and autonomously generates pull requests through multi-stage AI workflows (plan, code, review, publish).
Apple Studio Display XDR receives FDA clearance for medical imaging feature to support radiologist workflows.
Identity infrastructure framework for autonomous agents handling credentials, delegation, and permissions using OAuth 2.1 and SPIFFE standards.
P: AWS state machine language for formally modeling distributed systems with PeasyAI for AI-assisted code generation via Claude.
VOID: Netflix's physics-aware video editing tool using VLM reasoning to identify causal effects and guide diffusion for object removal.
Technical guide on three memory architecture approaches for AI companions: pgvector semantic memory, scratchpad, and filesystem-based context.
Article discussing data needs for understanding AI's impact on employment, mentioning researcher perspectives on economic disruption.
Research paper studying how AI aggregation affects social learning and knowledge via DeGroot model extension.
Fashion app using Meta's Segment Anything model to digitize wardrobes and suggest outfit combinations via natural language.
Email infrastructure API with SDKs for multiple languages, positioning itself as unified alternative to Postmark/Mailchimp for AI-native applications.
Early-stage PHP package manager alternative to Composer with improved performance.
Technical deep-dive implementing bfloat16 floating point arithmetic from scratch, covering design challenges.
JitAPI is an MCP server enabling Claude to dynamically interact with APIs by semantic search over OpenAPI specs, reducing token usage by 34x.
Personal account of returning to work after illness, asking about AI tools for accessibility.
Tool to use GitHub Container Registry as a Nix binary cache via OCI blobs and GitHub Actions.
Web tool implementing Paul Graham's intellectual CAPTCHA concept using logic puzzles and fact-checking to improve social network discourse.
Personal project to open-source medical records as LLM wiki for rare neurological condition research, still in early stage with privacy concerns.
Claim of building a cognitive architecture on a Mac with 60+ modules, IIT-based consciousness simulation.
Freestyle: cloud platform providing sandboxes and infrastructure for running AI coding agents at scale.
Complaint about Google suspending a startup's email account without human support.
PostgreSQL extension in Rust for full-text search in Kazakh language, handling agglutinative morphology via PGRX.
Opinion piece on misuse of code coverage metrics and how to improve measurement practices.
Android app using NFC tags to block distracting apps with physical friction. Minimalist design.
Ninthwave: Orchestration layer for parallel AI coding that generates reviewable PRs while maintaining user control and existing tools.
Deep Extract: Agent-in-the-loop extraction tool with autonomous verification cycles for structured data extraction accuracy.
Forge tool to replace manual context management in Claude Code. Addresses context window limitations and project continuity for AI-assisted development.
Satirical dialogue between LLMs discussing global crises. Opinion piece, not technical content.
Workspace manager for parallel coding agent development. Linux GTK app and CLI for managing git repos, worktrees, and isolated terminal sessions.
Claude agent that automatically analyzes iOS/Mac performance traces from Instruments. Exports to DuckDB for SQL-based diagnostics.
Static analysis tool that builds dependency graphs to identify files needing review before code changes. Open source, 97% precision across 16 repos.