Modem released its MCP server and public API for all users, enabling coding agents to search synthesized customer feedback from Slack, Intercom, Linear, and other sources in a single call. The company…
A senior AI engineer argues that the biggest source of unnecessary LLM cost in production AI agents is not the model choice but the retrieval strategy, citing that a smarter query planning approach ca…
GitHub reported that its Copilot model Anthropic Fable is experiencing elevated errors, with users able to subscribe to email or SMS notifications for updates on the incident.…
A senior test automation engineer who built a five-agent SDLC pipeline over the Model Context Protocol reports that the most expensive failure mode in multi-agent pipelines is not model error but comp…
EY has deployed an 'invisible' AI router that has helped cut token consumption by up to 60% since its global rollout in April, according to Dan Diasio, EY's global consulting AI leader. The router sit…
NightRun, an experimental open-source UEFI application, boots a Raspberry Pi 5 or x86_64 PC directly into a local large language model without a conventional operating system, loading quantized models…
Focal Harvest, a new open-source Python CLI tool, automates web research and OSINT collection by querying search engines, scraping pages, and synthesizing findings into Markdown reports with multi-LLM…
FreshSaaS.online, a platform for discovering new software tools, features multiple AI-related launches including deltafin, an open-source project that runs Kimi K3, a 2.8T-parameter Mixture-of-Experts…
Independent developer Daniel Ioni from Rimini, Italy, has launched MyZubster, an open-source ecosystem that combines global mapping of plants and animals with private Monero payments and human-control…
X launched an encrypted Chat API and software development kit on July 30th, enabling developers to build customer-support bots, automated services, and AI agents inside X Chat. The API encrypts messag…
OpenAI quietly open-sourced its Codex Security CLI and TypeScript SDK on GitHub and npm under Apache 2.0 on July 28, 2026, but the tool requires a paid subscription to the Codex Security service to pr…
A developer has released claude-code-merge-queue, a TypeScript tool that serializes commits from parallel Claude Code agents on a single machine, after running four to five agents pushing up to 90 com…
Seafile has launched SeaTicket, an AI agent tool that aggregates context from GitHub, Discord, email, and forums to help open-source teams resolve support issues faster. The tool can close duplicate r…
A developer released claude-code-merge-queue, a free local merge queue that serializes landings from parallel Claude Code agents to prevent push races and build flakiness. The tool runs entirely on th…
Unblocked, a context engine provider, argues that connecting AI agents to sources via MCP connectors gives access but not understanding, costing up to 83% slower task completion and 60% more tokens. I…
A hands-on test pitted open-weight Kimi K3 against Claude Opus 5 on generating a fully explorable 3D world from a single reference image using the Klein agent harness. Opus 5 produced a more polished …
1Password has released SuperSAGE v2, an AI-powered security code review pipeline that solves context-window limits and nondeterminism by generating incremental, compressed scaffolding files per source…
Block's open-source project Goose is moving to an issues-first contribution model, replacing pull requests as the primary mechanism for outside contributions, because coding agents have made producing…
Conductor released version 0.78.0, introducing Conductor Cloud, a platform for cloud workspaces that run in isolated sandboxes and persist when users close the app. The update also launches the Conduc…
Reused input dominates token bills because every API call resends the full conversation history, with one Codex user recording 3.59 billion reused tokens out of 3.77 billion total in a single day. Ant…