A three-person team built ReviewAssist, an MCP server that integrates into Claude coding sessions to fix code and provide guided PR walkthroughs, aiming to reduce time spent on pull requests and cut c…
Keenable's new SELECT system lets AI agents run read-only DuckDB SQL queries against live web data, combining search, page fetching, and semantic extraction in a single query. The MCP server-based ser…
Google begins automatically upgrading Search campaigns using campaign-level broad match or automatically created assets to AI Max in September 2026, while Microsoft's similarly named AI Max for Search…
Neo4j published a startup guide for building graph applications on its Aura cloud database, recommending installation of the Neo4j CLI and agent skills first, then using the neo4j-getting-started-skil…
Neon, the serverless Postgres provider, has renamed its CLI from neonctl to neon and introduced new commands for agent tooling, branch-first workflows, and diagnostics. The CLI now supports one-shot s…
A developer's portfolio agent answers questions using only 0.598% of its 1,003 indexed chunks, yet reports answers with the same confidence as if it had read the entire corpus, a flaw the developer sa…
Models with fewer than 1 billion parameters, such as LFM 2.5 350M, exhibit unreliable tool calling in agentic systems, prompting developers to implement repair mechanisms and prompt-checking systems i…
LiquidAI's LFM 2.5 1.2B, a 1.2-billion-parameter model that is 696 MB on disk, can power agentic systems with modifications to an MCP server, according to a developer's test. The model required adding…
JetBrains' refactoring-skill benchmark, published August 19, 2026, reports that its AI skill for Rider and ReSharper is 83% faster, 64% cheaper, and uses 63% fewer tool calls, based on median results …
ChatGPT cannot edit videos because it lacks the tools to open footage, cut timelines, or export files, and its only workaround is generating ffmpeg commands that re-encode files and lack professional …
Firebase's Agent Skills library raised a coding agent's task pass rate from 31.7% to 78.0% in the company's own evaluations, according to an Aug 11 blog post by product manager Charlotte Liang. The ga…
The Internet Computer Protocol (ICP) has launched a Model Context Protocol (MCP) server in public preview, enabling AI agents like Claude to discover canisters, resolve identities, query data, and exe…
A developer reports that Ling 3.0 Tiny, a model by Ant Group related to Alibaba, now works with llama-cpp via a GGUF file, and it performs fast and accurate tool calling on their MCP server. The devel…
Medusa, the open-source commerce platform, has launched a new migration tool within its Medusa Cloud MCP server that lets AI agents migrate store data from WooCommerce to Medusa. The tool by default m…
Elastic, the Search AI Company, is hiring a Senior Software Engineer for its Integrations Team in Barcelona, Spain, to build the Elastic MCP server and universal agent skills platform, working primari…
A developer fixed a bug in the DEV.to MCP server's update_article tool, which previously fired unnecessary GET and PUT requests with empty payloads. The fix added a guard to prevent empty payloads, bu…
Faisal Iitian released MindCache, a Python SDK with an MCP server for long-term memory in LLMs, reporting a 64% average rubric pass rate on his BEAM evaluation versus about 53% for Mem0. The system us…
CortexBrain, an open-source monitoring platform for distributed cloud and hybrid cloud-edge workflows, integrates eBPF to provide kernel-level insights and network observability without sidecar overhe…
Flare removed its AI-generated error solutions in April 2024, citing that they lacked context and took up UI space, and replaced them with an MCP server, a CLI with an agent skill, and a 'Copy for AI'…
A developer using the LFM 2.5 2.6B model with llama-cpp found that adding detailed descriptions to JSON schema parameters improved tool call correctness from 0% to nearly 100%, enabling the use of a f…