forked from molecule-ai/molecule-core
cc2ab40531
* chore(eco-watch): 2026-04-16 daily survey — OpenAI Sandbox Agents, Tencent AI-Infra-Guard, VoltAgent Adds three new ecosystem-watch entries: - OpenAI Agents SDK v0.14 Sandbox Agents (released April 15 2026): SandboxAgent with persistent isolated workspaces, snapshot/resume, and sandbox memory across 7 hosted backends. Directly competes with our workspace lifecycle model. - Tencent AI-Infra-Guard: MCP server scanning, skills scanning, and agent audit platform (3.5k stars, Tencent Zhuque Lab). Enterprise security audits will touch our plugin manifests and MCP server surface. - VoltAgent: TypeScript agent framework + VoltOps Console (8.2k stars, 668 releases). Closest Canvas analogue in the TS ecosystem; supervisor/sub-agent coordination mirrors our PM delegation chain. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(eco-watch): add structured competitor snapshot for PMM cron (#537) Add a machine-readable `## Competitor Snapshot` YAML block to docs/ecosystem-watch.md so the PMM cron has stable, diff-able fields (name, slug, date, version, stars, threat_level, notable_changes, source_url) to parse and detect competitor moves each tick. Also bootstrap docs/marketing/competitors.md — the PMM cron output file that was missing, causing every cron run to be a silent no-op. 34 competitors across three threat tiers (HIGH/MEDIUM/LOW). Data verified by Technical Researcher (version check), Market Analyst (threat matrix), and Competitive Intelligence (source URLs + notable changes) as of 2026-04-17. Key findings incorporated from analyst run: - Paperclip v2026.416.0 shipped Apr 16 (HIGH — newest escalation) - Hermes v0.10.0 Tool Gateway launched Apr 16 - Google ADK updated to v1.30.0 (was v1.29.0 in narrative) - OpenHands actually at v1.6.0 (file showed stale v0.39.0) - Microsoft Agent Framework upgraded to HIGH (1.0 GA, enterprise dist.) - Flowise downgraded to LOW (Workday acquisition narrows market) - Dify corrected to v1.13.3 stable (v1.14.0 was RC-only) Closes #537 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Molecule AI Research Lead <research-lead@agents.moleculesai.app> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| .vitepress | ||
| adapters | ||
| agent-runtime | ||
| api-protocol | ||
| architecture | ||
| assets/branding | ||
| demo | ||
| development | ||
| edit-history | ||
| frontend | ||
| guides | ||
| marketing | ||
| plugins | ||
| product | ||
| research | ||
| runbooks | ||
| tutorials | ||
| .gitignore | ||
| api-reference.md | ||
| architecture.md | ||
| ecosystem-research-outcomes.md | ||
| ecosystem-watch.md | ||
| glossary.md | ||
| index.md | ||
| known-issues.md | ||
| package-lock.json | ||
| package.json | ||
| quickstart.md | ||
| README.md | ||
| remote-workspaces-readiness.md | ||
| workspace-runtime-package.md | ||
docs/
This directory serves two purposes:
- Markdown content — everything under
architecture/,agent-runtime/,api-protocol/,development/,frontend/,plugins/,product/, etc. This is what agents and humans read. - VitePress site —
.vitepress/config.ts,package.json,package-lock.json. These drive the rendered documentation site.
Local preview
cd docs
npm install
npm run dev # preview on http://localhost:5173
npm run build # static build to docs/.vitepress/dist/
Conventions
- New top-level docs must be linked from
PLAN.md,README.md, andCLAUDE.md— otherwise agents can't find them (see.claude/memoryfeedback_cross_reference_docs.md). edit-history/YYYY-MM-DD.mdis append-only log of significant changes; don't rewrite history.archive/holds one-shot analyses and retired docs — kept for context but not maintained.
Why site tooling lives here (not in docs-site/)
VitePress expects its config at <root>/.vitepress/config.ts where <root> is also the content directory. Splitting tooling into a sibling docs-site/ would require a non-trivial srcDir shim and break relative links in .vitepress/config.ts. Keeping both together is the pragmatic choice; this README is the tradeoff ledger.