Full-text search across 25785 articles. Combine with topic and date filters; results sorted by relevance.
Promptloop, a new interactive CLI tool built on LangChain's deepagents framework, enables developers to create, run, and improve prompt evaluations entirely from the terminal. The tool saves methodology, test cases, repo…
AI researchers face growing moral pressure as their work shapes the most powerful technology ever created, with top companies fighting lawsuits over data centers, AI safety, and military use. Researchers Daniel Kokotajlo…
Vidai Community Edition, a free Rust-based AI gateway for personal, evaluation and non-commercial use, is now available. The binary provides production-grade features including one-line integration, in-path cost attribut…
Second-brain-mcp is a self-maintaining personal knowledge database that uses MCP, DuckDB, and biological memory models to automatically link, compress, and index saved papers, notes, and figures. The tool fetches full-te…
The coding agent Zot now supports Claude Opus 4.8, adding the model to its catalog of over 20 providers including OpenAI, Google Gemini, and local models. The lightweight terminal agent, distributed as a single static Go…
Claude Opus 4.8 dynamic workflows enable users to spawn hundreds of parallel sub-agents for large-scale tasks, reducing completion times from hours to minutes. The system uses a three-layer architecture with an orchestra…
Cognition co-founder Walden Yan and OpenInspect's Cole Murray discussed the rise of "async agents" — AI coding tools that operate in the background rather than requiring constant developer oversight — in a podcast releas…
Recursive self-improvement (RSI) has emerged as the new buzzword in artificial intelligence, with startups like Recursive Superintelligence and researchers including Richard Socher and Andrej Karpathy racing to build AI …
SigNoz has released a guide for instrumenting CrewAI with OpenTelemetry to enable real-time observability into agent, model, and tool performance across AI workflows. The integration allows users to export traces, logs, …
Sanofi has built its own internal AI ecosystem called Concierge, used by 60,000 employees, after its chief digital officer deemed existing enterprise AI tools "lame" and limited in value. The French pharmaceutical giant …
A developer building a production-grade AI agent in public has released Phase 1 of the CloudSeven Agent project, a foundational CLI chatbot for a fictional airline called CloudSeven Airlines. The project, tagged at v0.1.…
A developer has released SirenSpec, a YAML-first SDK that treats production AI "agents" as workflows with fixed sequences of LLM calls and branching logic. The tool allows entire pipelines to be defined in a single reada…
Cadence v8.4, an open-source coding harness, now routes different software development lifecycle roles to different AI models, allowing Claude to write code, Codex to review it, and Bugbot to triage issues. The developer…
Indian IT giants TCS, Infosys, Wipro, and Tech Mahindra are positioning themselves to solve the AI deployment crisis facing U.S. companies, where 95% of generative AI pilots fail due to poor integration. The $300 billion…
Lago released an open-source SDK that wraps existing LLM clients to automatically extract token usage data and send it to Lago's billing platform without requiring middleware or API changes. The SDK supports AWS Bedrock …
A developer compared the costs of Claude Sonnet 4.6 API at $3.00 per million input tokens against a self-hosted Llama 3.2 90B instance on a $20/month DigitalOcean GPU Droplet. The analysis found that Claude API is cheape…
Nexus, an open-source AI gateway, now intercepts enterprise large language model traffic at the SDK, network, and OS layers to enforce compliance, audit, and control policies across all LLM applications. The gateway norm…
A new benchmark from the Agent Voyager Project found that a simple "double-check your work" instruction added to an AI agent's prompt boosted its accuracy from 82% to 95% on a PDF-to-webpage conversion task. The winning …
A developer built a local 3-billion-parameter language model that matches Claude Sonnet on quality for summarization and classification tasks, runs twice as fast, and costs nothing per call. The model was selected and va…
Nilbox launched a desktop sandbox that runs untrusted AI agents inside a full virtual machine with real VM isolation, not containers. The tool uses a zero-token architecture where API keys never enter the guest environme…