ai-frameworks - The LGTM (Page 2)

The LGTM

Sign in Subscribe

ai-frameworks

A collection of 119 posts

Mastra 1.35 Turns Fine-Grained Authorization From Route Metadata Into Runtime Coverage

Mastra 1.35 Turns Fine-Grained Authorization From Route Metadata Into Runtime Coverage

Mastra 1.35 is the kind of release that looks like framework plumbing until you imagine it missing in production. The headline is not a new agent demo, a shinier chat UI, or another claim about autonomous work. It is authorization coverage: the unglamorous question of whether every protected route

Agno 2.6.7 Adds User Isolation and URL Fetch Guardrails Because Agent Platforms Are Becoming Multi-Tenant Web Apps

Agno 2.6.7 Adds User Isolation and URL Fetch Guardrails Because Agent Platforms Are Becoming Multi-Tenant Web Apps

Agno’s v2.6.7 release is a useful reminder that “agent framework” has become too small a phrase for what these projects are building. Once a system stores sessions, memories, traces, approvals, knowledge, workflow runs, and user-facing APIs, it is not just an SDK. It is a multi-tenant web

Composio Fixes a One-Field MCP Schema Bug That Was Breaking the Tool Layer Agents Actually Depend On

Composio Fixes a One-Field MCP Schema Bug That Was Breaking the Tool Layer Agents Actually Depend On

Composio’s CLI beta release looks almost comically small until you read the bug it fixed. A strict schema expected MCP tool output parameters to look one way. Some MCP-backed tools returned an empty object instead. The result: execution through the higher-level SDK path broke across MCP tools that agents

LiteLLM 1.85 Ships the AI Gateway Release That Treats Routing, MCP Auth, and Supply Chain Verification as the Same Production Problem

LiteLLM 1.85 Ships the AI Gateway Release That Treats Routing, MCP Auth, and Supply Chain Verification as the Same Production Problem

LiteLLM’s latest release is not interesting because it added another knob to a model router. It is interesting because the project is starting to look like the place where the uncomfortable parts of production AI systems all collide: routing policy, MCP authentication, observability semantics, budget controls, and supply-chain verification.

OpenAI Agents SDK Turns Absolute Sandbox Paths Into a Coding-Agent Trust Boundary

OpenAI Agents SDK Turns Absolute Sandbox Paths Into a Coding-Agent Trust Boundary

The OpenAI Agents SDK just patched the kind of bug nobody puts on a conference slide and everybody depends on in production: a sandbox path invariant. PR #3422 changes WorkspacePathPolicy so it rejects relative sandbox workspace roots. The stated problem is simple: the helper methods are documented and used as

DeepAgents Code 0.1.1 Fixes the URL Fetch Boundary Coding Agents Cannot Hand-Wave

DeepAgents Code 0.1.1 Fixes the URL Fetch Boundary Coding Agents Cannot Hand-Wave

The most important DeepAgents Code release this week is not the one that made the product line cleaner. It is the one that fixed a URL-fetching tool. LangChain released deepagents-code==0.1.1 with two patches: a corrected LangSmith sandbox working directory and a guard for the fetch_url tool

LangChain Splits DeepAgents CLI From DeepAgents Code, and That Boundary Is the Product Strategy

LangChain Splits DeepAgents CLI From DeepAgents Code, and That Boundary Is the Product Strategy

LangChain’s deepagents-cli==0.1.0 release looks tiny until you read the removal notice. The package no longer ships the interactive TUI or coding-agent surface. It now keeps only deploy and supporting configuration, while users who depended on the chat REPL, sessions, MCP tooling, skills, and widgets are told

Microsoft Agent Governance Toolkit Moves Agent Security Into the Middleware Path Where It Belongs

Microsoft Agent Governance Toolkit Moves Agent Security Into the Middleware Path Where It Belongs

Agent security is finally moving out of the prompt and into the execution path. That is the important part of Microsoft’s new Agent Framework and Agent Governance Toolkit integration: not that Microsoft has another safety checklist, but that the policy decision happens before the agent acts, inside the runtime