Full-text search across 35589 articles. Combine with topic and date filters; results sorted by relevance.
Open-weights models like Llama and Mistral give developers control over the inference stack, enabling custom quantization, KV cache optimization, and hardware-specific tuning that closed APIs cannot match, according to a…
A developer reports that shifting to a hybrid AI workflow using Anthropic's Claude 3.5 Sonnet for architectural planning and a local Llama 3.1 8B model for unit test generation reduced token spend by nearly 40% without n…
Amdb, a zero-runtime, single-binary code context MCP server that indexes codebases entirely on the local machine with combined graph and vector retrieval, has been released as an open-source tool. The Rust-based tool req…
Open Design, an open-source desktop app from nexu-io/open-design, lets users turn any coding agent into a design engine and exports real files like HTML, PDF, PPTX, and MP4. The app avoids proprietary formats and lock-in…
A developer built a usage analytics system for Claude Code agents by reading the transcript_path from the Stop hook payload and accumulating agent invocations into a JSONL log. The system has recorded 553 invocations, re…
Developer Alex Cloudstar is launching a YouTube series where he builds software entirely without AI assistance, aiming to test whether his programming skills have eroded from over-reliance on AI tools. The experiment, do…
Anthropic detailed the containment architectures it uses for Claude across web, developer, and desktop products, arguing that agent safety depends on deterministic limits on filesystem, network, and execution environment…
A single attack payload hijacked Claude Code and OpenAI's Codex unchanged, according to an exploit brief published July 9 by Boyan Milanov and Heidy Khlaaf at the AI Now Institute. The 'Friendly Fire' exploit, which the …
A developer who runs over 10 AI coding agents in parallel found that the bottleneck is not the AI but human attention and context switching. The engineer spreads agents across multiple machines but struggles to track wha…
A developer built OtterKit, a tunnel and webhook toolbox that turns the mechanical debugging loop for webhooks into automatable commands. The tool generates correctly-signed synthetic events locally, enabling test-driven…
A developer created a setup to run two Claude Code subscriptions on one machine by using separate config directories and symlinks, allowing seamless switching between accounts while sharing skills, MCP servers, and setti…
A developer built an MCP wrapper to expose Eclipse JDT Language Server to Claude Code, enabling AST-aware Java refactoring. The bridge gives the AI agent direct access to Java compiler APIs for precise semantic searches …
A developer built tearsheet, an MIT-licensed MCP server that provides local, keyless web scraping for Claude Code. The tool avoids API keys, quotas, and telemetry by running entirely on the user's machine, and is designe…
A developer built a crew of four AI agents—Logic Reviewer, Style Reviewer, Performance Reviewer, and a Moderator—to simulate real team code review, then used SigNoz and OpenTelemetry to trace and debug the multi-agent sy…
Hivemind, a self-hosted MCP server for coding agents, provides a stale-proof shared memory store that prevents agents from acting on outdated or unverified information. The system uses an absolute-relevance abstention ga…
A developer outlines 8 production TypeScript and Model Context Protocol (MCP) patterns for 2026, including monadic Result types, type-safe MCP handlers, and resilient LLM circuit breakers, to eliminate spaghetti async co…
Retok, a zero-dependency Python CLI tool that analyzes token efficiency and cost from Claude Code and OpenAI Codex CLI usage logs, is now available as an open-source project on GitHub. The tool scans transcripts to measu…
Syntra, an open-source terminal-first control plane for multi-model coding, is now in early public beta. The tool routes planning, execution, and review tasks to separate AI models, storing durable typed state files inst…
AMD released an update to its Radeon Developer Tool Suite (RDTS) featuring Radeon GPU Profiler (RGP) 2.7, which now displays DirectX 12 HLSL shader source code alongside GPU instructions. The update also adds an Average …
A developer compared Playwright MCP and Playwright CLI for use with Claude Code, finding that CLI uses approximately 26,000–27,000 tokens per multi-step UI test versus MCP's 114,000 tokens, a difference of nearly 90,000 …