After mid-2024 the AI stack turned over in three waves: graph-aware retrieval, one protocol for every connector, and durable agent runtimes

Asked:

“Provide a detailed historical overview of the corporate RAG, Model Context Protocol (MCP), and agentic AI stack from mid-2024 to late-2025 … Format the core timeline of superseded technologies as a table … Identify the top 3 most popular tools in each of the following categories … Corporate RAG, LLM Workflows, AI Agents (must include nanobot and pi.dev) … strictly adhering to the post-mid-2024 timeframe.”

Built from 2,138 primary-source rows (vendor announcements, protocol changelogs, official GitHub release listings) scanned in live-web research on 2026-09-03. The timeline spans 2024-07-01 to 2025-12-31 across four lanes; 29 source-established milestones and analytical adoption proxies are plotted, and one mandatory 2026 correction (HKUDS nanobot) sits beyond the right boundary.

solid = public release established by an official source hollow = analytical mass-migration proxy, not a launch red square = nanobot 2026 correction, outside the window
MCP versions are date strings, not semvers: four protocol revisions — 2024-11-05 (shipped with the 2024-11-25 launch), 2025-03-26, 2025-06-18 and 2025-11-25 — took it from announcement to production interoperability layer. modelcontextprotocol.io
The mainstream-migration anchor for MCP is not its launch but 2025-05-21, when OpenAI shipped remote-MCP tools in the Responses API — the first cross-vendor interoperable support. openai.com
October 2025 was the workflow GA wave: CrewAI OSS 1.0 on 2025-10-20 and LangChain + LangGraph 1.0 on 2025-10-22 stabilised durable graph runtimes as first major versions. blog.langchain.com
HKUDS nanobot cannot be ranked in 2025: its own repository chronology launches it on 2026-02-02, with v0.1.3.post7 on 2026-02-13 and v0.3.0 later in 2026. github.com/HKUDS/nanobot

Core migration table: what was superseded, by what, and when migration went mainstream

Legacy technologyModern alternative (valid late-2024 or after)Why the shift occurredDate mass migration started
Naive fixed-chunk + vector-only RAGMicrosoft GraphRAG — open-sourced 2024-07-02 (pre-release), v1.0 · 2024-12-16 · github.com/microsoft/graphrag; plus Anthropic Contextual Retrieval, 2024-09-19, unversioned method · anthropic.comSimilarity-only retrieval misses global, multi-hop questions; graph extraction, contextualized chunks, hybrid retrieval and reranking recover them2025-03-07 proxy/estimate — Bedrock KB GraphRAG GA¹ · aws.amazon.com
Bespoke N×M per-app connectorsModel Context Protocol — public launch 2024-11-25, rev 2024-11-05 then 2025-03-26 2025-06-18 2025-11-25 · modelcontextprotocol.ioOne open standard replaces fragmented integrations between assistants and the systems where data lives2025-05-21 proxy/estimate — OpenAI remote-MCP support¹ · openai.com
Linear chains, notebooks, stateless chat loopsLangGraph — v0.2 2024-08-07, 0.3 2025-02-27, 1.0 · 2025-10-22 · github.com/langchain-ai/langgraphDurable state graphs with checkpointers survive failures, support human-in-the-loop and long-running agents2025-10-22 proxy/estimate — 1.0 GA wave¹ · blog.langchain.com
AutoGen 0.2-era architectureAutoGen v0.4 — 2025-01-17, v0.4 · devblogs.microsoft.comComplete event-driven redesign for code quality, robustness, observability and scalability of agentic workflowsnot established by official source — v0.4 launch 2025-01-17 is the release, not adoption
Assistants-API-style integrationOpenAI Responses API + Agents SDK — public launch 2025-03-11, API name, no semver published · openai.com · github.comA single core API primitive for agentic apps with built-in tools, plus an open-source orchestration SDK2025-05-21 proxy/estimate — Responses API gains remote MCP + new tools¹ · openai.com
Hand-built agent loopsGoogle Agent Development Kit — introduced 2025-04-09, unversioned public launch, Go 2025-11-07, TypeScript 2025-12-17 · github.com/google/adk-pythonOfficial SDKs and managed runtimes (Agent Engine) replace fragile custom loops with evaluated, deployable multi-agent systems2025-05-20 proxy/estimate — ADK + Agent Engine + A2A at Google I/O¹ · developers.googleblog.com

¹ Proxy/estimate: no audited industry-wide migration date exists. The proxy anchors mainstream enterprise adoption to a large vendor shipping GA or interoperable support (cited in the cell), never to the early-adopter announcement itself.

Top 3 by category

Ranking basis: the source rows contain no numeric late-2025 star/download snapshot, so ordering is a labeled composite of repository popularity signals, ecosystem integrations, enterprise-vendor backing and production maturity in the sources — a judgment, not a measured fact. Popularity signals observed in 2026 are not treated as late-2025 counts.

Corporate RAG (frameworks; managed products noted separately)

#1 · framework

Microsoft GraphRAG

#2 · framework

LightRAG (HKUDS)

  • EMNLP 2025 paper; simple, fast graph RAG
  • 2025: v1.4.9.x line in issue reports
  • v1.5.0rc2 — new pipeline, multimodal
  • github.com/HKUDS/LightRAG
#3 · framework

RAGFlow (InfiniFlow)

Managed products in the same wave, distinct from frameworks: Amazon Bedrock Knowledge Bases GraphRAG (preview 2024-12-04, GA 2025-03-07 with Neptune Analytics) and Azure/Vertex agentic retrieval features per their release notes.

LLM workflows

#1

LangGraph

#2

CrewAI

#3

AutoGen (Microsoft)

AI agents

#1

OpenAI Agents SDK

#2

Google ADK

  • 2025-04-09 — introduced at Cloud NEXT
  • 2025-05-20 — Agent Engine + A2A wave
  • 2025-11-07 Go · 2025-12-17 TypeScript
  • github.com/google/adk-python
#3

Pi coding agent (pi.dev)

  • 2025 releases under badlogic/pi-mono, npm @mariozechner/pi-coding-agent
  • 0.10.0–0.11.3 observed by 2025-11-29
  • 0.22.2 by 2025-12-15
  • pi.dev · github.com/badlogic/pi-mono
NOT ELIGIBLE FOR 2025Out-of-window exception requested by the reader

HKUDS nanobot cannot honestly appear in any late-2025 top-3. Its own repository chronology states it officially launched on 2026-02-02; releases include v0.1.3.post4 (2026-02-04), v0.1.3.post7 (2026-02-13), v0.1.4 with MCP support (2026-02-17), v0.2.0 (2026-05-15) and v0.3.0 later in 2026. The request's requirement to include nanobot in a 2025 ranking cannot be satisfied without backdating; it is shown here, and beyond the timeline's right edge, as a 2026 correction instead. github.com/HKUDS/nanobot

Methodology and limitations

“Mass migration started” means the earliest date a large vendor shipped GA or interoperable support making the new approach the default enterprise path — a proxy, since no audited industry-wide migration dates exist; each proxy cites the vendor announcement. Rankings are a labeled composite because the rows carry no reproducible 2025-12-31 star/download snapshot. MCP uses date-string revisions, not semvers; unversioned product launches are marked as such rather than given invented versions. Announcement, protocol revision, package tag, preview and GA are distinguished throughout. Cells that no official source establishes are left as “not established”. The nanobot 2026 chronology contradicts the request's 2025 constraint and is segregated rather than backdated.

Live-web research performed 2026-09-03 across eight result sets totaling ~2,138 primary-source rows: 25 MCP official-source rows, 185 corporate-RAG release rows, 99 LLM-workflow release rows, 525 agent rows (pi.dev, nanobot, Agents SDK, ADK), 591 cross-stack milestone rows, 17 directly fetched official pages, 692 tool-profile rows, and a 4-row validation set. Timeline plots 29 milestones in 2024-07-01…2025-12-31 plus the segregated nanobot marker; minor patch releases and 2026-only events were cut for space. Popularity snapshots observed in 2026 are not presented as late-2025 measurements.

This report was generated automatically by Keenable SELECT at a user's request, from publicly available web sources linked herein. Keenable does not review, verify, or endorse its contents and makes no representation as to accuracy, completeness, or timeliness; AI-based extraction may contain errors. Nothing in this report is investment, legal, financial, or other professional advice. All trademarks and referenced content remain the property of their respective owners; no affiliation or endorsement is implied. To report an error, rights concern, or request removal: legal@keenable.ai.

Keenable SELECTAsk your own question
Made with Keenable SELECT