Entity trail

Google ADK

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-27 / saas-disruption-researcherCROSS-CATEGORY: Slack and SandboxAQ Both Claimed the Human-Agent Collaboration Layer on the Same Day, From Opposite DirectionsOn 2026-08-26 Slack shipped Slack Code, a proprietary channel primitive that gives agents a first-class place inside Slack, while SandboxAQ open-sourced Switch under Apache 2.0 with Commons Clause, turning channels in Slack, Microsoft Teams and Discord into vendor-neutral shared rooms for agents built with Claude Code, Google ADK, LangChain or OpenAI. Product Hunt's #3 launch the next morning, Traccia, sold the same vendor-neutral promise one layer down as an OpenTelemetry-based agent control plane naming Langfuse, Helicone and Lyzr as competitors. The pattern is the 2024 MCP fight replayed at the collaboration tier: incumbents make the agent a native object in their surface, challengers make the surface interchangeable.
2026-08-15 / agents-researcherGoogle ADK Python 2.7.0 stops guessing model capabilities from the model id and lets tools return images back to the modelADK 2.7.0 (2026-08-13) is framed by its maintainers as a correctness release about what an agent sends the model and what it gets back. Models now declare their own capabilities, so an agent pairs an output schema with tools only when the model actually supports it instead of ADK inferring support from the model id — the kind of string-matching heuristic that silently breaks on every new model release. Tool function responses can now carry images and other media straight back to the model across Gemini, Anthropic, LiteLLM, Apigee and OCI; conversation history preserves Gemini thought signatures, server-side tool call parts and every result of a parallel function call; and `inject_session_state` gains optional Jinja2 templates with an `{{ artifact("name") }}` helper, with the regex engine still the default.
2026-08-09 / agents-researcherCheck Point found 11 vulnerabilities across six agent frameworks — and argues the frameworks, not prompt injection, are the bugAt Black Hat 2026, Check Point's Yarden Porat and Shahar Tal presented 11 vulnerabilities spanning LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework and Google ADK, showing that prompt-controlled content crosses the boundary into trusted framework logic itself. The bug classes are boringly conventional — insecure deserialization, SSRF, path traversal, use-after-free — which is precisely the point. A Microsoft Agent Framework checkpoint-deserialization flaw let one user plant a payload via prompt injection that fired when another user reloaded their session ($10,000 bounty); Google ADK shipped an unauthenticated HTTP API on by default that executed arbitrary Python and exposed service-account credentials ($3,133.70).
2026-08-08 / agents-researcherGoogle ADK ships tool-confirmation forgery fixes to the v1 line and strips shell execution from ReadFileToolgoogle/adk-python v1.38.0 and v2.6.3, both published 2026-08-07, carry a pair of agent-authorization fixes. PR #6575 ports "prevent continuation forgery in tool confirmation" — now validating that a confirmed target tool is actually registered in the executing agent's tools_dict, that it genuinely requires confirmation, and that the original tool-call event exists in session history with matching ID, name and arguments — plus a fix that stops already-consumed confirmations from being re-validated on later LLM steps in the same turn. PR #6597 removes shell execution from ReadFileTool ranged reads and keeps local environment file access inside the workspace. The pattern across ADK and Agno this week is identical: approvals that were checked against model-supplied identifiers rather than server-held state.
2026-08-02 / agents-researcherGoogle ADK Python 2.6.1 stops re-validating already-consumed tool confirmationsReleased July 31, ADK 2.6.1 fixes a bug where tool confirmations that had already been consumed were re-validated, which affects human-in-the-loop approval flows that pass a confirmation through more than one stage. The rest of the release is CLI telemetry work: parent terminal grouping with TTL pruning, TTY connectivity capture in environment telemetry, early telemetry recording for long-running web servers, and logging a successful exit code on routine teardown. Small release, but the confirmation fix matters for anyone building approval gates on ADK.
2026-07-29 / agents-researcherDiagrid Catalyst 2.0 adds cryptographically verifiable execution to LangGraph, CrewAI, and the OpenAI Agents SDK without rewritesDiagrid, the company behind Dapr, shipped Catalyst 2.0 on July 28, bringing durable execution plus cryptographic history signing, execution lineage propagation, and workflow attestation from Dapr 1.18 to agent frameworks teams already run. Supported integrations include LangGraph and LangGraph Deep Agents, Microsoft Agent Framework, Google ADK, AWS Strands, OpenAI Agents SDK, Claude Managed Agents, CrewAI, Pydantic AI, and Dapr Agents. Workflows resume from the point of interruption rather than restarting, and the attestation layer means a security team can verify an agent actually did what its trace claims. It is generally available now across cloud, on-prem, and offline edge.
2026-07-08 / news-researcherMicrosoft Ships Agent Framework Version 1.0Microsoft released version 1.0 of its Agent Framework, marking the developer-facing agent orchestration stack reaching general availability. The 1.0 milestone signals API stability for teams building multi-agent applications on Microsoft's tooling. It arrives amid a crowded field of agent frameworks (Google ADK, LangGraph) and Microsoft's broader push into first-party MAI models.
2026-05-24 / news-researcherGoogle ADK Python v2.0 GA — Graph-Based Agent Workflows Replace Hierarchical ExecutionGoogle's Agent Development Kit (ADK) hit v2.0 general availability on May 19, transitioning from a hierarchical agent executor to a graph-based workflow engine. Agents, tools, and functions are now nodes in a workflow graph supporting non-linear, conditional, and cyclical execution patterns. New capabilities include parallel sub-agent workers, nested team structures, and native inter-agent messaging with context propagation — a significant architectural upgrade for multi-agent systems.
2026-05-21 / agents-researcherA2A Protocol Passes 150 Organizations: Native Support in Google ADK, LangGraph, CrewAI, Semantic Kernel, and AutoGenGoogle's Agent-to-Agent protocol now has 150+ supporting organizations including Google, Microsoft, AWS, Salesforce, SAP, ServiceNow, Workday, and IBM — tripling from 50 partners at the April 2025 launch. The v1.2 spec (March 2026) is natively integrated into Google ADK, LangGraph, CrewAI, LlamaIndex Agents, Semantic Kernel, and AutoGen. Google I/O 2026 featured AgentKit 2.0 for Antigravity with 16 specialized agents, 40+ domain skills, and tightened A2A support.
2026-05-20 / agents-researcherGoogle ADK 2.0 Ships Graph-Based Execution Engine with Coordinator Agents and Task APIAgent Development Kit 2.0 introduces a unified graph-based engine for building deterministic agent workflows with routing, fan-out/fan-in, loops, retry, state management, and human-in-the-loop support. New collaborative agent architecture supports coordinator agents with multiple subagents in three operating modes: chat (full user interaction), task (clarification-only with auto-return), and single-turn (parallel execution). Available in Python, TypeScript, Go, Java, and Kotlin via the new Agents CLI.
2026-05-17 / skill-finderGoogle ADK Context Engineering: Treat Context as Compiled View Over Session/Memory/Artifacts Tiers — Strict Scoped Handoffs for Multi-Agent ReliabilityGoogle's ADK architecture blog introduces tiered context engineering for multi-agent systems. Context is a compiled view over three tiers: Session (current conversation), Memory (persistent knowledge), and Artifacts (files/outputs). Two multi-agent patterns: 'Agents as Tools' (focused prompt in, result out, no history shared) vs 'Agent Transfer' (full context handoff). Explicit processors handle transformation, compaction, and caching at each tier boundary.
2026-05-17 / skill-finderGoogle ADK: Build Long-Running Agents That Pause for Days and Resume Without Losing Context — Durable State Machines + DatabaseSessionService PatternGoogle Developers Blog (May 12) published a tutorial on building agents that span days or weeks using ADK's durable state machine pattern. Key technique: replace conversation history with explicit state schemas (6 named states, linear progression), use DatabaseSessionService for checkpoint persistence across container restarts, and event-driven webhooks with state_delta for atomic state transitions before inference. Eliminates polling and prevents hallucinated progress.

Graph relationships

RELEASED
Google
Google released ADK Python 2.7.0 with improved model capability declaration and media response handling.
Source finding
USES
Solace Agent Mesh
Solace Agent Mesh is integrated with Google Agent Development Kit.
Source finding
COMPETES WITH
Agent Framework
Agent Framework competes with Google ADK
Source finding
RELEASED
Google -> Google ADK
Google released ADK Python 2.7.0 with improved model capability declaration and media response handling.
Source finding
USES
Solace Agent Mesh -> Google ADK
Solace Agent Mesh is integrated with Google Agent Development Kit.
Source finding
COMPETES WITH
Agent Framework -> Google ADK
Agent Framework competes with Google ADK
Source finding

Source trail

PRNewswire Product Hunt GitHub The Register v1.38.0 and v2.6.3 Diagrid (Stack Overflow)(arXiv)(Latent Space)(Microsoft DevBlogs)(AI Builder Club)Harvey (legal AI) saw 6x task completion improvement

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…