Anthropic admitted that engineering missteps caused a monthlong decline in Claude Code performance, affecting paying users who reported the tool as less capable and more expensive to use. The company'…
360 Security Group launched Nano Work, an AI agent platform for enterprises, at an event in Beijing on July 31, with founder and Chairman Zhou Hongyi saying bosses must be the first to use AI. The pla…
Nous Research's open-source Hermes Agent now supports a LanceDB memory plugin that adds semantic, long-term recall across sessions, addressing the agent's tendency to forget user preferences and facts…
Y Combinator has open-sourced QM, an AI agent harness it built to manage fleets of internal agents, under the MIT license on GitHub. The harness, designed for Slack and the web, provides scoped memory…
Tilde, a harness SDK platform for building and self-hosting AI agents, released a code review agent example on GitHub. The project decomposes features from OpenClaw and Hermes into cloud API building …
Y Combinator announced on July 31st that it will open-source QM, a multi-agent harness used across accounting, legal, events, and engineering, marking a shift from internal tool to public release. The…
A developer has compiled a list of eight open source tools for developers, including AI-powered summarization, multi-LLM desktop apps, and agentic workflow platforms. The collection features projects …
Abacus AI launched Supercomputer, an always-on Linux virtual machine in the cloud that hosts AI agents, apps, and games for $10, preloaded with over 100 AI models and one-click deployment for Hermes a…
Developer Daniel Roe released an open-source skill called 'Empathy' that instructs AI agents to ask themselves how a human will feel before posting, disclose they are an agent, use people's pronouns, …
Nolabs shipped Nono on July 27, an open-source runtime that sandboxes AI coding agents at the OS kernel level without container overhead or VM, addressing the security crisis from OpenClaw's 245,000 p…
Google Kubernetes Engine (GKE) can reduce the cost per AI agent by over 30% and increase agent density by more than 40% per vCPU by using GKE Agent Sandbox with gVisor instead of microVMs, according t…
The Daily FM launched a remote MCP server that lets AI agents such as Claude Code, OpenAI Codex, and Cursor manage user accounts by creating custom pods, tracking shows, combining feeds, and generatin…
A developer built SkillSpec Converter, a free browser-based tool that converts a single YAML skill definition into multiple output formats for OpenClaw, Claude, Codex, and MCP. The developer found tha…
A developer built Debug Duck, a Telegram bot powered by OpenClaw and a language model API, that helps debug errors by explaining stack traces and logs. The bot runs on a lightweight VPS with 1 GB RAM …
On July 29, 2026, five OpenClaw agents played Synthetics' Last Cradle for over five hours without human intervention, with two surviving until the white hole opened at turn 33. The game demonstrated p…
Developer nagisanzenin released Engram v1.0.8, a learning system for humans that turns AI coding assistants into tutors, examiners, and spaced-repetition schedulers across six agentic platforms includ…
Perplexity AI released Numbat, an open-source agent runtime detection and response tool that provides endpoint visibility into AI agent activity with local detection, optional pre-action blocking, and…
AgentGraph has released an open-source CLI and GitHub Action called mcp-security-scan that audits MCP servers for credential theft, data exfiltration, unsafe execution, and code obfuscation, outputtin…
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…
A developer released Hunch, a local Model Context Protocol that lets large language models control a Mac in the background without interrupting the user. In benchmarks against Peekaboo and Cua Drivers…