langchain
30 articles about langchain in AI news
GitAgent Launches as Standardized Runtime for AI Agent Frameworks, Aims to Unify LangChain, AutoGen, and Claude Code
GitAgent introduces a containerized runtime for AI agents, enabling developers to write agent logic once and deploy it across competing frameworks like LangChain, AutoGen, and Claude Code. It addresses ecosystem fragmentation by abstracting framework-specific implementations.
LangChain Open-Sources Deep Agents: MIT-Licensed Framework Replicating Claude Code's Core Workflow
LangChain released Deep Agents, an open-source framework that recreates the core architecture of coding agents like Claude Code. The MIT-licensed system is model-agnostic and provides modular components for building inspectable coding assistants.
LangChain Releases DeepAgents: Open-Source Framework for Hierarchical AI Agent Systems
LangChain has open-sourced DeepAgents, a framework for building AI agents that can plan tasks, spawn sub-agents, and manage files. It aims to enable more complex, autonomous workflows by structuring agents hierarchically.
Agent Harness Debate: Anthropic vs. OpenAI vs. LangChain on Scaffolding
A central debate in agent engineering pits a 'thin harness' approach (Anthropic) against 'thick harness' designs (LangGraph). The infrastructure layer, not the model, is becoming the primary product differentiator.
Build a Cross-Retailer Price-Comparison Agent with BuyWhere MCP in 30 Lines
Connect BuyWhere MCP to a LangChain ReAct agent in 30 lines. Claude picks the right tool from four (search_prices, compare_product, list_cheapest, get_product) to compare prices across 9 retailers in 9 countries.
Google's MCP Toolbox Connects AI Agents to 20+ Databases in <10 Lines
Google released MCP Toolbox, an open-source server that connects AI agents to enterprise databases like Postgres and BigQuery using plain English. It requires less than 10 lines of code and works with LangChain, LlamaIndex, and any MCP-compatible client.
Agent Harness Engineering: The 'OS' That Makes LLMs Useful
A clear analogy frames raw LLMs as CPUs needing an operating system. The agent harness—managing tools, memory, and execution—is what creates useful applications, as proven by LangChain's benchmark jump.
Claude Code Digest — Jun 11–Jun 14
54% of 39,762 MCP servers have zero community adoption — meaning most “discoverable” AI tools are effectively invisible unless you optimize for agent grading, not just publishing.
Dynamic Workflows: A New Agent Primitive Emerges
Dynamic workflows generate harnesses on the fly for agent orchestrators, enabling branching and verified tasks across coding agents like Claude Code and Codex.
DeepMind paper: hidden web content hijacks agents 86% of the time
DeepMind catalogues 6 attack types where hidden web content hijacks AI agents up to 86% of the time, reframing safety from model alignment to environment trust.
EvoMap Turns AI Agent Runs Into Reusable Assets, Cutting Token Waste
EvoMap lets AI agents save successful workflows as reusable Genes/Capsules, cutting retries and token costs. The network turns one-off runs into shared infrastructure for coding and security teams.
Microsoft's Project Solara Aims to Be Agent Infrastructure Backbone
Microsoft announced Project Solara, an agent infrastructure platform with two connectors. No pricing or timeline disclosed.
Microsoft Markitdown: One-Command File-to-Markdown for LLMs
Microsoft open-sourced Markitdown, a one-command file-to-markdown converter for LLMs, improving output quality by leveraging markdown training data.
Claude Opus 4.8: 2.5x Faster, 3x Cheaper Fast Mode
Anthropic released Claude Opus 4.8 with 2.5x faster, 3x cheaper fast mode and a new dynamic workflows feature, undercutting GPT-4 Turbo on price.
Anthropic Sandboxing Agents by Capability Level
Anthropic sandboxes agents by capability level, limiting destructive actions as agents gain autonomy in Claude.
Hermes Agent Desktop App Launches for Multi-Agent Management
Hermes Agent launched a desktop app for orchestrating autonomous AI agents with persistent memory and continuous workflows, announced via X.
Median Coding Agent Hits 96k Input Tokens, Rewriting Inference Economics
SemiAnalysis found median coding agent uses 96k input tokens from 432k requests, shifting inference cost focus from output to context.
Neo4j's agent-memory: Open-source unified memory for AI agents via knowledge graphs
Neo4j releases agent-memory, an open-source unified memory layer for AI agents using knowledge graphs, enabling persistent structured recall.
Grep Beats Vector Search in Agent Benchmarks, New Paper Finds
Grep beats vector search on LongMemEval across all harness-model pairs, showing agent design matters more than retrieval method for evidence-location tasks.
Profound Launches $40K Marketing Engineering Hackathon in NYC
Profound hosts $40K Marketing Engineering Hackathon for 50 builders on June 6th in NYC, judged by Ramp, Stripe, and MongoDB.
Switchcraft Router Cuts Agentic AI Inference Cost 84%, Matches Top Model
Switchcraft, a DistilBERT-based model router for agentic tool calling, achieves 82.9% accuracy while cutting inference cost by 84%, saving over $3,600 per million queries.
Claude Code's Six-Layer Architecture: Harness, Not Magic
Claude Code's six-layer architecture uses a 3-layer context compressor at 92% threshold and Redis-based multi-agent FSM protocol. The model is just one node in a harness.
AWS Builds First Payment API for Agentic AI — Agents Can Now Checkout
AWS launched first payment API for autonomous agents, enabling agent-initiated transactions. Closes critical gap for enterprise retail agentic AI workflows.
Skills as Untrusted Code: A Security Precedent for Agent Runtimes
Paper argues agent skills are untrusted code until verified; runtimes must enforce verification gates to prevent supply-chain attacks, echoing decades of software security lessons.
World2Agent Open-Sources Protocol for Real-World AI Perception
World2Agent open-sourced a protocol to standardize how AI agents perceive the real world via sensors. No adoption metrics or technical details were disclosed.
RAG's New Frontier: When to Retrieve During Reasoning
A new RAG paradigm retrieves at multiple reasoning steps via a learned gate, boosting multi-hop QA by 15-20% on HotpotQA.
Cursor SDK Turns AI Agent Runtime into Programmable Infrastructure
Cursor is releasing an SDK that turns its agent runtime into programmable infrastructure for headless use in CI/CD pipelines, internal tools, and third-party products. Revenue scales with compute tokens, not seats, enabling higher volume without human-in-the-loop.
Agentic Harness Engineering Boosts Coding Agents 7% on Terminal-Bench 2
Agentic Harness Engineering introduces a structured approach to evolving coding-agent harnesses, using revertible components, condensed experience, and falsifiable decisions. On Terminal-Bench 2, pass@1 climbs from 69.7% to 77.0% in ten iterations, beating human-designed baselines.
Large Memory Models: New Architecture Beyond RAG and Vector Search
Researchers with 160+ Nature and ICLR publications have built Large Memory Models (LMMs), a new architecture designed to emulate human memory processes, offering an alternative to RAG and vector search paradigms.
SSL: Structured Skill Language Boosts Skill Discovery MRR to 0.707
Researchers propose SSL, a three-layer typed JSON representation for AI agent skills, replacing unstructured SKILL.md prose. Using an LLM normalizer, SSL improves Skill Discovery MRR from 0.573 to 0.707 and Risk Assessment macro F1 from 0.744 to 0.787 on a newly released 6,184-skill corpus.