🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
chore(ai-team): 0.3.1 for #3995 #3996 #3997 #4004 (changelog)
rffe7b6f93dd3
diff --git a/plugins/ruflo-ai-team/.claude-plugin/plugin.json b/plugins/ruflo-ai-team/.claude-plugin/plugin.jsonindex 831b1e0877..40241ed820 100644--- a/plugins/ruflo-ai-team/.claude-plugin/plugin.json+++ b/plugins/ruflo-ai-team/.claude-plugin/plugin.json@@ -1,7 +1,7 @@{"name": "ruflo-ai-team","description": "Give Claude a tenant-isolated AI team that divides work, coordinates progress, recalls approved context, and returns evidence-backed results.",- "version": "0.3.0",+ "version": "0.3.1","author": {"name": "ruvnet","url": "https://github.com/ruvnet"diff --git a/plugins/ruflo-ai-team/CHANGELOG.md b/plugins/ruflo-ai-team/CHANGELOG.mdindex 04ea758c51..8780c3a13b 100644--- a/plugins/ruflo-ai-team/CHANGELOG.md+++ b/plugins/ruflo-ai-team/CHANGELOG.md@@ -2,6 +2,13 @@Newest first. One `## <version> — <date>` heading per version, then `feat:`, `fix:`, `breaking:` and `chore:` bullets (ADR-478). Built from git history; older versions: `git log -- plugins/ruflo-ai-team`.+## 0.3.1 — 2026-10-12+- fix: stored teams, runs, tasks and memories no longer share mutable objects with the caller or with exported snapshots (#3995)+- fix: run evidence includes the task history of the run in its audit trail (#3996)+- fix: re-remembering a memory keeps its original creation time (#3997)+- fix: a pending vector index build can no longer restore an invalidated tenant index (#4004)+- chore: thanks to @rudycelekli for all four fixes+## 0.3.0 — 2026-10-09- feat: skills, commands and agents name the connector tools in plain language instead of Claude Code namespaced identifiers (allowed-tools lists only the portable Read tool; the repo audit requires the field), so they read correctly on claude.ai and Cowork- feat: lifecycle skill covers run_complete (the tasks_incomplete rule); skills state the real status values, template ids and budget range