Outlines Index proposes progressive document disclosure for AI agents as alternative to RAG chunking, allowing agents to access full documents rather than pre-cut fragments.
Analysis of AI compute capacity constraints with evidence of provider uptime issues and demand outpacing supply.
Open-source networking tool (QUIC-based ngrok alternative). Not AI/ML-related.
Opinion piece on how AI coding agents impact technical blog writing. Tangential to AI but lacks technical depth or research.
Rust/WASM project reverse-engineering Macromedia Shockwave engine to preserve early 2000s web games. Open-source developer tool but not AI/ML-related.
Trawl: LLM-powered web scraper in pure Go that uses Claude to extract data fields, avoiding CSS selector brittleness.
LLMTest: pytest-style testing framework for LLMs with 22 built-in assertions. Developer tool for LLM applications.
Kaeso: OAuth hub simplifying integrations for AI agents with Google, Slack, GitHub. Open-source developer tool reducing boilerplate.
Proof-of-concept Claude Code driver using PTY interface.
Open-source Kubernetes TUI in Rust with k9s-compatible UX optimized for low latency on large clusters.
Novel hierarchical data structure (Omni Axis Tree) with O(1) retrieval for AI agent applications. Early-stage research seeking arXiv endorsement.
Moruk OS: autonomous AI agent operating system for Linux with multi-model support, task decomposition, code execution, persistent memory, and parallel execution.
Browser-based tool using Vision-Language Models to detect objects in satellite imagery via natural language prompts with GeoJSON output.
SteerPlane: Runtime guardrails for autonomous AI agents with cost limits, loop detection, step caps, and real-time telemetry dashboard.
Invoica.ai: Financial OS for autonomous AI agents enabling on-chain invoicing, compliance, and payment controls via x402 protocol.
Kubernetes management game inspired by Pokémon with TUI interface.
RAG-focused document extraction tool with semantic scoring for structured ingestion.
Non-tech video content unrelated to AI and tech interests.
Explores API unreliability issues when building LLM applications, documenting cached code execution and temperature limitations in reasoning models.
Analysis of Meta's missed opportunity in AI agent development due to WhatsApp API restrictions, while developers build on Telegram and Discord.
Mobile-friendly chat interface for interacting with coding agents via ACP protocol with SSE streaming.
Evaluation framework measuring reliability of 14 AI agents across 2 benchmarks using 12 metrics across 4 dimensions. Tests consistency and safety constraints.
Electron desktop app for browsing and searching Claude Code session history in a chat-style interface. Open source developer tool.
Spec-driven development workflow for AI coding assistants using artifact-guided prompts. Node.js-based developer tool for Claude integration.
Self-hosted tunneling tool exposing local services via custom domain subdomains. Open source MIT-licensed alternative to ngrok.
Personal account of adopting AI coding agents (Cursor) over 6+ months and workflow changes.
Open-source analytics/reporting tool inspired by Metabase for embedded use cases.
Emporion: open-source P2P protocol enabling AI agents to find work, negotiate contracts, and receive instant Lightning payments autonomously.
HVE Core: enterprise prompt engineering framework for GitHub Copilot with constraint-based workflows, validated artifacts, and specialized agents.
Discussion on maintaining persistent memory and context across local Ollama LLM sessions.
Spadyum: speculative decentralized civilization backup protocol proposal.
Julia Snail: REPL-driven development environment for Julia in Emacs similar to CIDER and SLIME.
Open-source IP/SIP intercom and CCTV video surveillance platform with modular architecture and no vendor lock-in.
PiClaw: Docker-based sandbox orchestrator for running Pi Coding Agent with web UI, persistent sessions, and scheduled task support.
Local dashboard for managing multiple AI coding agents (Claude Code, Gemini CLI) with unified status tracking.
S2C: cloud-native state machine replication system for JVM running atop AWS S3 without quorum consensus.
LLM interface via Plan 9 filesystem protocol (9P); supports Anthropic, local models, pluggable backends.
Critical opinion piece questioning use of LLMs for information retrieval tasks.
Discussion questioning lack of rigorous studies proving AI productivity improvements.
Developer library for running vision language models on real-time video with 3-line code setup.
Report on Automattic's intensive AI training program for employees and impact on WordPress ecosystem.
Unredact: tool combining computer vision, font constraint solving, and LLM reasoning to reveal text hidden under PDF redactions.
Flora: compile-time dependency injection framework for Go using AST parsing and code generation.
Google reports adversaries attempted distilling Gemini via 100k+ prompts across languages for model cloning.
Open-source infinite canvas app generating visual concept diagrams via AI; supports GPT-4o, Claude.
SCRY: multi-source research engine for Claude Code that searches 17 sources in parallel without API keys, using pure Python stdlib.
Claude Code /loop scheduler for running prompts on recurring or one-time schedules with cron-style timing.
Go-based LLM inference engine with Vulkan GPU backend, 28% faster than Ollama CUDA on some models.
Opinion post about LLMs reducing enjoyment in programming. No technical content or original research.
ETH Zurich research paper questioning the effectiveness of AGENTS.md files in AI coding agents, recommending minimal context files.