Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-09-03 · source-backed
anthropics/commerce-agents is at 1.1k stars under Apache 2.0, pairing a customer-facing shopping agent with a back-office merchant agent, each implemented three ways: raw Messages API turn loop, Claude Agent SDK, and hosted Managed Agents with MCP servers. Four worked verticals ship (retail, travel, telecom, entertainment) with fencing and provenance gates, memory validation and tool-call verification across all three paths. Reference implementations showing the same agent three ways are rare and useful.
Each link below shares sources, entities, or timing with this story.
synthetic-sciences/openscience (Apache 2.0, v1.3.4 on July 11, 2,501 stars since July 3) runs the full loop, literature review through hypothesis, code, experiments on real compute, and written findings, with 290+ skills and 30+ databases including UniProt, PDB, ChEMBL, arXiv,...
Monid sells runtime pay-per-call access to 1,800+ APIs with no per-vendor subscription, $1 in free credits to start, listing Merge, ApyHub, Eden AI and Firecrawl as comparables (Product Hunt). SandrPod runs the unmodified e2b and e2b-code-interpreter SDKs against your own infr...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
Triple-stream retrieval (BM25 keyword, vector embeddings, knowledge-graph traversal) fused via Reciprocal Rank Fusion on the iii engine, with SQLite for state and an in-memory vector index, no external database. The economic claim: ~170K tokens/year (~$10) versus ~650K tokens...
1. Flip your multi-model pipeline to review-then-generate. Instead of using a reasoning model to plan before code generation, let the specialist generate freely and use reasoning tokens for review. Paper shows 90.2% pass@1 vs 87.2% for the planning pattern. Source 2. Audit you...
Three separate Anthropic changes over about two weeks point the same direction, and none of them announced themselves as a strategy. Claude Code 2.1.238 added claude self-hosted-runner --defer-shutdown-max-min, which keeps serving attached sessions on SIGTERM, parks whatever's...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.