Run a configurable research-and-writing crew for a marketing-strategy draft
The open-source example separates agent roles and task configuration for producing a marketing strategy and related content from user-supplied business inputs.
Topic
open-source use cases: 14 examples
Source-linked workflows that name open-source. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
OpenGCUA + MAI-Gym: Alibaba open stack for generalist computer use
Tongyi-MAI open-sources OpenGCUA (GUI+code harness, harness-to-model decisions, cross-device SDK; OSWorld-v2 +19.6 pts / −53% steps across 8 models) and MAI-Gym (up to 20k parallel RL envs; MAI-Gym-9B 78.4% MobileWorld / 76.2% OSWorld-Verified). Code + arXiv:2610.22200 / 2610.20939.
Tracekit 1.2.3: tamper-evident flight recorder for AI agents
MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
Weatherdeck: read-only status board for AI coding-agent lanes
Show HN Weatherdeck (Oct 16): a read-only TV/phone status board fed by small pushers that shows which coding-agent lanes are waiting on you, honest progress ranges, silent sources, and deferred/owned work—not monitoring/alerts; demo mode with ship-deck theme; open source on GitHub.
UseAgent: open-source shared workspace for Claude Code/Codex/OpenCode/Pi
AGPL self-hostable workspace runs Claude Code, Codex, OpenCode or Pi in isolated sandboxes; hand off from Slack/web/API, attach playbooks/skills/knowledge, approve sensitive actions, and get PRs or files back—positioned as an open Devin alternative.
DeltaBox Lite: diff/commit/abort sandbox for coding agents
Apache-2.0 agent-native sandbox (Linux FUSE/Landlock, macOS APFS clones+Seatbelt) gives agents a confined FS view with unified text diffs, binary markers, and per-task or per-tool-call commit/abort—optional JSON-RPC adapters for Pi and policy for secrets/network.
OpenDesign Motion: open-source local alternative to Claude Motion
OpenDesign v0.25.0 (Oct 15) ships OpenDesign Motion—an open-source, local-first alternative to Claude Motion: prompt for editable animation source plus MP4, five bundled examples (Motion Future, Product Promo, Showreel, UI Morph, Visual Lesson), motion skills in the @ picker, and agent-native use of whatever coding agent is on PATH (BYOK).
Perplexity SPACE: open-source Firecracker sandboxes for agent code
Perplexity open-sourced SPACE (Sandboxed Platform for Agentic Code Execution)—the Firecracker microVM sandbox behind Computer—under Apache 2.0 on Oct 15, 2026: HTTP/SSE APIs to create Linux environments, run commands, and manage lifecycle; partners CoreWeave, Akamai, and Crusoe plan to offer it; Semafor reports 0/118 breakout attempts vs other sandboxes in Perplexity’s tests.
OpenUI 1.0: MIT generative UI runtime so agents render interfaces not text
Thesys’s OpenUI hit 1.0 (Oct 15): models stream OpenUI Lang into your registered React components (cards/forms/charts); Lang 1.0 adds defineAction/defineFunction, library.extend, and stored messages; CLI scaffolds apps and setup-agent writes AGENTS.md for Claude Code/Codex/Cursor—vendor tiktoken bench claims ~53% fewer tokens vs JSON-render formats.
jevcrawl: web crawler MCP with no LLM in the crawl loop
Show HN: jevcrawl (Apache-2.0 MCP + CLI) crawls for a goal and returns only relevant passages—small Jev model picks links/passages instead of Claude in the loop; README claims ~2× answer-page hit rate vs Crawl4AI and ~10× cheaper per answer than LLM-driven crawl; tools: crawl/scrape/map.
OpenCode 2.0: one local service, Code Mode MCP, background subagents
Anomaly OpenCode 2.0 (Oct 12; changelog still shipping 2.0.x Oct 16): auto-started local background service shared by TUI/web/desktop; rewritten API + @opencode/client; @opencode/codemode turns MCP/OpenAPI into scriptable functions (all MCP servers default to Code Mode); background subagents + async shell; 80+ hot-reload plugins; @opencode/sdk for embed. Upgrade: `opencode upgrade --major`.
Garuda: open-source coding agent with OS-level sandbox
Apache-2.0 terminal/VS Code/Zed agent (ACP) runs commands under Seatbelt/bubblewrap so writes stay in project+temp+caches, network is closed unless allowlisted, edits ask first, team policy can't be loosened by a cloned repo, and an outside hash-chained audit log verifies with /audit verify.
Moyai: LiteLLM open-sources its self-hosted cloud coding agent
LiteLLM open-sourced Moyai—the Devin-like cloud agent they run in production: Slack/browser tasks get isolated cloud workspaces (terminal+FS+browser), run Codex/Claude Agent SDK/Hermes/OpenCode, open PRs, and attribute spend through your LiteLLM gateway (they estimate ~79% lower vs their Devin bill).
OpenAPPA: deterministic flow-label guardrails that don't break agents
Open-source MIT guardrail tracks audience×trust labels across tool calls (algebra, not LLM-as-judge), returns remedy plans (sanitize/authority/subagent) so agents keep ~90% task completion with 0% exfil on their benches—plugs via pre/post tool hooks; docs also as MCP.