Full-text search across 8053 articles. Combine with topic and date filters; results sorted by relevance.
A developer spent a week testing OmniRoute, a free, MIT-licensed open-source AI gateway that unifies 1200+ models across 359 providers behind a single endpoint with no inference markup. The review found quota-aware auto-…
OpenAI released GPT-6 Astra, its new flagship model, alongside cheaper GPT-6 Sol and Luna tiers and a GPT-6.1 Sol upgrade, while Anthropic shipped Claude Opus 5.5 and Claude Sonnet 5.5, according to the August and Septem…
SpecterOps Consulting Services Intern Gavin Kramer told Let's Data Science that coding-agent session histories can expose active projects, developer intent and connected systems to an attacker who already has code execut…
SpaceXAI opened a public beta of Team Bots on September 28th, bringing shared AI teammates to its Teams and Enterprise plans that teams configure for recurring roles, equip with skills and business-tool access, and use t…
A developer released Charter, an open-source Python library that lets developers declare AI agent tools as Pydantic models instead of writing integration code, shipping with 549 tools across fifteen APIs on two dependenc…
Fabian Both released Jevpipe, an open-source Unix-pipe CLI that lets AI coding agents run fast, cheap yes/no and choice judgments over thousands of files, lines or records in one shell command. In a ripgrep 15.1 example,…
A software engineer's playbook argues teams can scale from single-digit to over 100 merged pull requests per day by treating coding agents as parallelizable for loops, running multiple agents simultaneously via git workt…
Nvidia Corp. announced the free, open-source Nvidia Open Agent Safety Platform, which enforces security rules across three layers — the agents, the compute and the hardware — built on its OpenShell runtime and the BlueFi…
NVIDIA announced the NVIDIA Open Agent Safety Platform, an open software platform and reference system design for securing AI agents from testing to deployment, built on the open source NVIDIA OpenShell secure runtime an…
Anthropic's Claude Opus 5.5 and Moonshot AI's Kimi K3 each independently found the same novel link-cable vulnerability in Pokémon Emerald and built a working worm that turns a victim's game into Tetris, according to a co…
A new open-source policy enforcement gateway intercepts every AI agent tool call and validates it against a Pydantic schema, an OPA policy, a SPIFFE/SPIRE cryptographic workload identity, and an ImmuDB tamper-evident led…
A developer detailed the design of an MCP gateway layer that sits between an agent host and a raw MCP server, adding per-key and per-team rate limits, budget caps, and one audit row per tool call. The writeup walks throu…
Agentboxd launched live on 24 Sep 2026, offering AI agents real email inboxes on its own mail servers at agents.agentboxd.com, created with a single API call via POST /v1/inboxes. The service authenticates inbound mail w…
A developer built ContextForge, a tool that snapshots a repository's file tree and key files to draft agent instruction files such as .cursorrules, CLAUDE.md, AGENTS.md and .github/copilot-instructions.md. The tool runs …
A developer building Deiko, a Mac app that turns on-screen pointing and speech into briefs for coding agents, added a memory layer that groups related briefs so agents retain context across sessions. The system uses Type…
A new AI starter pack offers a paste-in prompt for the ChatGPT or Claude desktop app that automates setting up an X feed for following AI discourse, built around a curated list of roughly 200 accounts spanning research, …
A federal appeals court in Washington ruled 2-1 on Friday that the Pentagon may keep Anthropic's Claude out of its supply chain, barring the military and its contractors from using Claude in Defense Department work. The …
The Linux Foundation's Tokenomics Foundation, launched in August 2026, held its first event, Tokenomicon + FinOps X, in Amsterdam on September 22–23, gathering more than 500 FinOps and tokenomics practitioners. The Found…
A developer outlined a pattern for letting AI coding agents deploy to self-hosted servers through the Model Context Protocol (MCP) without granting them root or shell access, using per-person, per-workspace bearer tokens…
Indirect prompt injection remains a real threat against most models but has dropped sharply on the newest ones, according to Gray Swan's ART and IPI red-team benchmarks: attackers with 15 tries succeeded against Claude O…