On April 20, 2026, Moonshot AI shipped Kimi Agent Swarm K2.6, featuring 300 parallel sub-agents and 4,000 coordinated steps per run. The system's effectiveness in East Africa is enhanced by a pre-exis…
Testing MCP servers with real AI models is essential because servers that pass wire-level tests can fail when models attempt to use them. A developer explains that the semantic layer—whether a model c…
Cortex, a new open-source memory system for AI agents, launched as a local-first, encrypted solution that runs entirely client-side in Rust with a 124KB WASM binary. It offers sub-millisecond latency,…
AgentNexus, a new open-source framework, coordinates multiple LLM agents by service boundaries rather than roles, enabling automatic diff-aware notifications when documents change. The system uses a v…
Infrawise, an MCP server providing infrastructure context to AI coding assistants, uses deterministic analysis instead of large language models to answer fact-based questions. The tool extracts data f…
A developer built Filomena, a harness to run multiple Claude Code agents from one terminal, but abandoned it after six months as Claude Code's native features rendered it obsolete. The project's core …
A developer is building AccInt, a local Work Model for agent-run work that aims to determine what an AI coding agent should learn after a failed run. The project focuses on capturing settled commitmen…
ProofLayer released ProofLayer Rules, an open-source runtime security layer for MCP servers and LangGraph agents that blocks prompt injection, jailbreaks, and tool abuse in real-time with sub-100ms la…
Technosive Ltd. released SentinelMCP, an open-source security firewall for AI agents using the Model Context Protocol (MCP). The tool enforces policies, redacts PII and secrets, and provides audit log…
Researchers introduced AgentBeats, a framework for standardized and reproducible evaluation of AI agents using judge agents and protocols A2A and MCP. A five-month competition with 298 judge agents an…
Anthropic released Claude Fable 5, its first Mythos-class model, which benchmarks over 10% better than Opus 4.8 on coding tasks and features a 1M context window and deep MCP integration for multi-agen…
A developer building RyTask, an open-source project tracker, created a CI gate that ensures every UI feature has a corresponding MCP tool, preventing drift between the application and its agent interf…
A developer built sessionmem, a local-first MCP server that gives AI coding assistants persistent memory by injecting compact session summaries at the start of each new session. The tool reduces token…
Robinhood and Coinbase have launched infrastructure allowing AI agents to directly access brokerage accounts and make trades, raising concerns about the lack of evidence that such agents can reliably …
A developer built ghostprobe, a red-team scanner for MCP servers that detects tool poisoning and the 'lethal trifecta' of data access, sink, and untrusted input. When pointed at real servers, it found…
A developer built an MCP server with 132 tools that gives AI assistants like Claude programmatic access to Cognigy.AI's management API. The server enables natural language control over conversational …
Claude Code orchestrated a 10-agent code review of loomcycle via MCP fan-out, with reviewers running concurrently inside loomcycle and findings consolidated into a report. The review covered 86 files …
A developer has created a 60-second audit script to measure the "MCP server token tax"—the context budget consumed by tool definitions before an agent performs any useful work. Running the script agai…
Docker Product Manager Cecilia Liu identified three key operational patterns to prevent MCP failures after presenting two real-world "horror stories" at the MCP Dev Summit North America 2026. The firs…
TetherDust, an open-source self-hosted AI analytics engineer, was released on Show HN, enabling AI agents to generate verifiable SQL and build interactive d3.js dashboards by bridging codebases and da…