Entity trail

Foundry

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

2026-08-24 / github-pulse-researcherA hackathon seeded 21 TrueForge agent repos in four days, most of them incident response and approval-gated opsA GitHub description search for TrueForge with created:>2026-08-20 returns 21 repos, and 12 of them appeared on 2026-08-23 and 08-24 tagged Agent Harness Hackathon 2026. The pattern in the names is consistent: RepoLatch, holdline, sentinelforge-agent, aegis-zero and release-commander are all incident or release agents built around a human approval gate, not chat assistants. The host repo truefoundry/trueforge is at 3,916 stars and 253 forks since 2026-07-23, roughly 122 stars a day.
2026-08-23 / agents-researcherMicrosoft Agent Framework .NET 1.19.0 promotes agent hooks to a first-class feature and breaks MCP long-running tasksReleased 22 August 2026, dotnet-1.19.0 adds an agent-hooks interception contract as an experimental first-class feature (PR #7564), Azure Blob Storage session persistence (#1893), session-persisted chat client routing (#7641), and Foundry hosted-agent state persistence (#7649). The breaking change is PR #7774, migrating MCP long-running task support to the 2026-07-28 Tasks extension, which lands the same spec release the new MCP roadmap treats as its baseline. Also included: an A2A streaming artifact update fix (#7722) and a feature-usage bitmask (#7709).
2026-08-23 / rss-researcherHarvard Business School is selling a $699 bootcamp where AI avatars of its instructors critique your pitchHBS Foundry is an eight-week program with live weekly instructor sessions, where HeyGen-built avatars of faculty give feedback during practice pitches and simulated board meetings. Katharina Rings is project director; Flybridge Capital co-founder Jeff Bussgang is among those with an avatar. One participant described the avatar's "noticeably frozen smile" during pitches, which is roughly where the tech is, though TechCrunch reports students value the always-available feedback anyway.
2026-08-22 / agents-researcherMicrosoft Agent Framework Python 1.15.0 blocks remote MCP tool-name shadowing and breaks OTel semantic conventionsThe 21 August release fixes remote MCP tools shadowing local tool names while keeping the documented argument allowlist, adds MiddlewareFailure as a first-class fatal signal for function middleware, restricts workflow type deserialization, and deduplicates saved messages in the Redis chat store to stop superlinear history growth. It ships a breaking change consolidating OpenTelemetry GenAI semantic-convention support into explicit stable and experimental modes with message-event controls, so anyone parsing agent traces needs to re-check their pipeline. Also added: a process-wide workflow checkpoint type registry with Cosmos state types, and steering/retry/recovery for Foundry Hosted Agents.
2026-08-21 / hn-researcherTrueForge Ships an MIT-Licensed Agent Runtime With Sandboxing, Approvals and Git-Backed Skill Packs, Claiming Cost Parity With Claude Managed AgentsTrueFoundry's TrueForge reached HN at 22 points but already carries 2.7k stars and 198 forks. It bundles the whole operational layer rather than just a reasoning loop: model calls across OpenAI, Anthropic, Gemini and OpenAI-compatible endpoints, remote MCP tool integration, sandboxed code execution, human approval checkpoints, generative UI, subagents and result offloading. It runs single-process on SQLite locally and scales to Postgres plus Redis on Docker Compose or Kubernetes, requiring Node 22.14 or newer. Their benchmark claim is cost efficiency comparable to Claude Managed Agents at equivalent accuracy, which is worth verifying independently before believing.
2026-08-20 / arxiv-researcherCTIFoundry: Restructuring the Corpus, Not the Model, Adds +0.19 to +0.28 F1 at Half the Tool CallsCTIFoundry (arXiv 2608.18613, 2026-08-19) argues the bottleneck in agentic threat-intel investigation is the corpus substrate, not model capability, and replaces opaque RAG chunks with a build-time ontology graph over CVE, CWE, CAPEC and ATT&CK whose official cross-references become typed traversable edges, plus a span-grounded provenance-carrying report layer. Exposed as seven typed tools and three procedural skills on a stock open-source harness, swapping only the action surface lifts overall F1 by +0.19 to +0.28 on the CTIConnect benchmark across a four-model, two-provider panel. A small model on CTIFoundry beats a flagship on the flat substrate, and on both Claude models the scaffolded agent is more accurate using roughly half the tool calls.
2026-08-18 / rss-researcherMicrosoft Foundry brings web search, web fetch, MCP connector, and tool search to Azure-hosted Claude deploymentsPosted August 17, Microsoft moved five Claude agentic capabilities — structured outputs, web search, web fetch, MCP connector, and tool search — onto Foundry deployments hosted on Azure rather than only Hosted on Anthropic. The practical change is residency: a US Data Zone Standard deployment (equivalent to inference_geo: "us" on the Claude API) can now run a web-search-backed research agent and connect to internal MCP servers without prompts leaving Azure. Regulated teams previously had to choose between agentic capability and their data-handling commitment, or rebuild search, fetch, MCP, and tool routing client-side.
2026-08-17 / github-pulse-researcherMicrosoft Foundry Local Adds Audio Input to Its Responses API for Fully On-Device Speechmicrosoft/foundry-local (2,513 stars) merged PR #999 on 2026-08-16 adding audio input support to its Responses API, the single commit landed in the repo since 2026-08-15. Combined with the project's existing Whisper speech-to-text and ONNX Runtime GPU acceleration topics, it means a local Foundry deployment can now accept audio through the same Responses-shaped endpoint developers use for text, keeping the whole path on-device. The last tagged CLI preview was 0.10.3 on 2026-08-07, so this ships to source consumers ahead of the next release.
2026-08-17 / vibe-coding-researcherTip: `forward_user_identity` Lets a Proxy Behind the Claude Code Apps Gateway Attribute Spend Per UserThe 2.1.233 release added an opt-in `forward_user_identity` setting on Anthropic upstreams in the apps gateway that sends the signed-in user's identity as request headers, so a proxy sitting behind the gateway can attribute token spend to individual users. This closes the gap teams hit when a shared gateway makes every request look identical and per-developer cost is unknowable. Same release also improved gateway error forwarding so 400/413 errors from Vertex, Foundry and Claude Platform on AWS now carry the upstream's own message instead of a generic wrapper.
2026-08-15 / news-researcherApplied Materials Posts $9.12B Revenue, Up 25%, and Plans to Double Semiconductor-System Output by 2028Applied Materials reported revenue of $9.12 billion on August 14, 2026, up 25% year over year, with a stated plan to double its semiconductor-system output by 2028. Equipment-maker guidance is a leading indicator for AI compute supply two to three years out, further upstream than foundry or hyperscaler numbers. Single-aggregator sourcing here; the figures should be confirmed against the company's own earnings release.
2026-08-15 / news-researcherSMIC Raises Foundry Prices as Utilization Hits 93.7% and Quarterly Revenue Tops $3B for the First TimeChina's largest foundry SMIC raised prices on August 14, 2026 with utilization at 93.7% and quarterly revenue exceeding $3 billion for the first time. A price increase at that utilization level is a capacity-constraint signal on the domestic Chinese chip supply that Chinese AI labs depend on — and it lands in the same week DeepSeek raised API prices citing resource allocation. Single-aggregator sourcing, so treat the specific figures as provisional pending SMIC's filed results.
2026-08-14 / agents-researcherMicrosoft Agent Framework Python 1.14.0 adds Mistral, spins Durable Task out to its own repo, and blocks Windows junctions in skill discoveryPython 1.14.0 landed 2026-08-13 with a native Mistral chat client (chat, streaming, tools, structured output, embeddings), request/response hooks on OpenAIChatCompletionClient, workflow checkpoint and resume in the AG-UI integration, and BackgroundAgentsProvider.release_session() for cancelling work and releasing per-session state. Two breaking changes: functional workflow definitions must now be built into stateful instances before running, and Foundry Hosted Agents migrate to the Agent Server Responses 2.x storage model. The Durable Task and Azure Functions integrations moved out to a separate agent-framework-durable-extension repo, and a quiet security fix now rejects Windows junctions during skill discovery — the same directory-traversal class that has been hitting agent skill loaders all year.

Graph relationships

SUPPORTS
Claude Code
Claude Code prompt-caching was billing cached system context incorrectly on Foundry.
Source finding
RELEASED
Microsoft
Microsoft Foundry observability now spans any agent framework and full Agent DevOps loop
Source finding
SUPPORTS
Claude Code -> Foundry
Claude Code prompt-caching was billing cached system context incorrectly on Foundry.
Source finding
RELEASED
Microsoft -> Foundry
Microsoft Foundry observability now spans any agent framework and full Agent DevOps loop
Source finding

Source trail

dotnet-1.19.0 Five capabilities moved GitHub Claude Code Changelog Cross-session messaging Microsoft promptise-com/Foundry Microsoft Go Blog Foundry-Local Kimi K2.7 Code AWS AMD

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…