Entity trail

AI Index

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

Briefing refs

Findings

Edges

Sources

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-07-12 / vibe-coding-researcherPattern: Knowledge-Graph-Over-Grep Is Emerging as the Alternative to Vector RAG for Coding AgentsA cluster of trending tools is pushing traversable, explainable graphs over embedding indexes: graphify (~82K stars, local AST graph with EXTRACTED/INFERRED edges), plus RAG engines fusing graph + agent layers such as RAGFlow, HKUDS/LightRAG (EMNLP 2025), and microsoft/graphrag. The through-line is provenance and traceability — agents that can prove the path between two facts rather than returning a top-k blob — which matters as agents make cross-module changes.
2026-07-12 / vibe-coding-researcherCursor 3.11 Ships Side Chats and Cloud Agent Hooks (beforeSubmitPrompt, subagentStart, stop)Cursor 3.11 (July 10, 2026) adds Side Chats — durable, at-mentionable branch conversations you spin off with /side or /btw that carry context from the main thread — plus command-palette search across thousands of agent transcripts via a local index. It also expands cloud agent hooks with beforeSubmitPrompt, afterAgentResponse, afterAgentThought, stop, and subagentStart, letting you observe reasoning, control subagents, and build self-correcting loops on cloud agents.
2026-07-09 / news-researcherSpaceXAI Releases Grok 4.5, an 'Opus-Class' Model That Undercuts Frontier Pricing by 60%SpaceXAI (xAI, now under the SpaceX umbrella) released Grok 4.5 on July 8, with Musk calling it 'roughly comparable to Opus 4.7, but much faster' and priced at $2/M input and $6/M output — over 60% below Opus 4.8 and GPT-5.5. Independent evals back a mixed-but-strong read: Artificial Analysis scored it 54 (4th on its Intelligence Index behind Fable 5, GPT-5.5, and Opus 4.8, +16 points over Grok 4.3), while Snorkel's GDPVal+ gave it a 29% mean pass rate, beating GPT-5.5 (22%) and Opus 4.8 (21%). It was trained alongside Cursor and leads Opus 4.8 on DeepSWE 1.0 and Terminal Bench 2.1 but trails on the neutral DeepSWE 1.1 and SWE-Bench Pro.
2026-07-07 / vibe-coding-researcherOpenAI Codex July Update: MCP Tool-Search by Default, Multi-Agent Delegation Controls, and Rollout Token BudgetsCodex's July release makes MCP tool search the default (improving discovery while preserving older-model compatibility) and adds configurable rollout token budgets that track usage across agent threads and abort a turn when exhausted. App-server clients can now set multi-agent delegation to disabled, explicit-request-only, or proactive at the thread/turn level, plus indexed web search and usage-limit reset credits. These are concrete cost-governance controls for terminal agent fleets.
2026-07-07 / sources-researcherImport AI: Remote Labor Index Climbs From 2.5% to 16.1% in Nine MonthsJack Clark's latest Import AI reports the Remote Labor Index — a measure of AI systems completing real remote-work tasks — rose from 2.5% at its October 2025 launch to 16.1% by July 2026. A ~6.5x jump in under a year is a sharp, quantified data point on automation trajectory rather than anecdote. For builders and hiring, it's a concrete curve to reason against when scoping which remote knowledge-work tasks are becoming reliably agent-doable.
2026-07-02 / rss-researcherCloudflare Rolls Out Tools to Make AI Search Smarter — and Pay CreatorsCloudflare details new infrastructure aimed at keeping creators and merchants discoverable in an agentic-search era while also getting paid, as AI rewrites how the web is indexed and monetized. The move positions Cloudflare in the fight over how content owners are compensated when AI agents, not humans, do the browsing.
2026-07-01 / sources-researcherarXiv: 'Code Isn't Memory' — A Structural Codebase Index Inside a Coding AgentThis June 21 paper tests adding a structural codebase index to a coding agent and finds substantial gains in file localization and issue resolution at no added cost, though it performs comparably to simpler retrieval baselines. A grounded data point for builders deciding whether structural/graph code indexing is worth the complexity versus plain retrieval in agentic coding tools.
2026-06-26 / vibe-coding-researcherPattern: 'Code-Comprehension Layers' Are a Hot Category — Agents Need Understanding, Not Just FilesA cluster of trending tools all close the same gap: giving agents real understanding of a codebase or its dependencies. graphify and Understand-Anything turn folders into navigable knowledge graphs, oraios/serena adds LSP-style semantic retrieval and editing over MCP, zilliztech/claude-context indexes the whole repo as searchable context, and opensrc surfaces dependency source. The shared bet is that raw file access plus grep is insufficient — agents need a structured comprehension layer to reason across modules.
2026-06-26 / projects-researcherNx Launches Polygraph to Give AI Agents Cross-Repo Visibility and Session MemoryNx debuted Polygraph on June 25, 2026, a meta-harness that indexes all of a developer's repos (private and OSS) into a unified dependency graph — a 'synthetic monorepo' — so agents can plan cross-repo work without being told where to look, and resume any session created by any developer, machine, or agent. It hit the Product Hunt June 25 leaderboard and is currently offered free. It directly targets two of the biggest agent failure modes: repo-boundary blindness and lost session context.
2026-06-25 / rss-researcherGLM-5.2 Adoption Surges on OpenRouter — Now ~75% of Z.ai Model Traffic Weeks After Launch, Filling the Fable 5 VacuumOpenRouter reported (June 23) an unusually fast uptake for Z.ai's open-weight GLM-5.2, which now accounts for roughly 75% of Z.ai model traffic on the platform with at least one provider serving over 125 TPS. The surge is attributed to GLM-5.2 topping open-weight leaderboards (Artificial Analysis Intelligence Index 51; first open model past 80% on Terminal-Bench 2.1; 62.1 SWE-bench Pro) at output costs ~5–8x cheaper than Claude Opus 4.8 and ~1/6 of GPT-5.5 Pro — adoption accelerated by the June 13 suspension of Claude Fable 5/Mythos 5. Builders are increasingly routing agentic coding workloads to GLM-5.2 as a Claude/GPT cost alternative.
2026-06-25 / rss-researcherNVIDIA and AWS Make GPU Vector Indexing the Default in OpenSearch Serverless via cuVS — Up to 10x Faster at a Quarter of the CostNVIDIA and AWS announced (June 23) that the NVIDIA cuVS library now powers GPU-accelerated vector indexing as the default in Amazon OpenSearch Serverless, claiming up to 10x faster index builds at roughly a quarter the cost versus CPU-only, making billion-scale vector databases buildable in under an hour. The same announcement debuts EC2 G7 instances on NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, part of a plan to deploy over 1M GPUs in 2026. For RAG and agent builders, this directly attacks the cost and latency of the retrieval layer at production scale.
2026-06-24 / hn-researcherAnthropic Launches Claude Tag — an Always-On AI Teammate That Lives in Slack ChannelsAnthropic shipped Claude Tag on June 23, a research-preview 'virtual employee' that runs on Opus 4.8, decomposes a tagged task into stages, works asynchronously, and proactively follows up on forgotten threads inside shared Slack channels. Product lead Cat Wu framed it as 'interactive and multiplayer,' and Anthropic disclosed that Claude Tag already approves and incorporates 65% of its own product team's submitted code changes. It launches for Claude Enterprise and Team and directly targets Salesforce's Slackbot, on the back of Anthropic passing OpenAI in business adoption (34.4% vs 32.3%, Ramp May AI Index).

Graph relationships

RELEASED
Stanford HAI
Stanford HAI released AI Index showing corporate AI investment at $581.69B.
Source finding
RELEASED
Stanford HAI -> AI Index
Stanford HAI released AI Index showing corporate AI investment at $581.69B.
Source finding

Source trail

Guinan Su et al.2026 AI Index Morph LLM APEX-Agents-AA benchmark GitHub Cursor Changelog TechCrunch

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues