# Xinwei Xiong **AI Product Systems Engineer | Agent Runtime / Native iOS / Full-stack Systems** I build resumable agent runtimes and native AI products with durable context, tool policy and background execution. https://github.com/cubxxw | https://cubxxw.com | 3293172751nss@gmail.com | +86 18672749565 | Shenzhen | Open to AI / Agent product systems roles > Moved from deployment, CI and open-source collaboration at OpenIM into an AI SaaS venture, then converged on durable context, agent runtimes and native AI products. The through-line is turning ambiguous workflows into resumable, verifiable systems. ## Experience ### getyak | Independent AI Product Engineer | Apr 2026 - present Independently shipping agent runtimes, native iOS and web products around durable context, with automated release, regression and artifact-verification workflows. Representative systems include DayPage and Agentry. ### Telepace AI | Founder / Product Engineer | Jun 2024 - Oct 2025 Founded an AI feedback analysis SaaS, owning the core backend, asynchronous data pipeline, system integration and Kubernetes delivery while collaborating on the web product. The stack worked end to end, but no first paying user emerged, so the initial venture stopped in 2025 and the lesson became explicit validation gates and kill criteria. ### The Plant | Engineering Team Member | Final year · 2024 · about 2 months Briefly joined the international team of a Tokyo-based commerce software company during the final university year, then moved into independent entrepreneurship. Exact dates, formal title and a representative outcome remain pending. ### OpenIM | Open-source Intern, then Community Contributor | Junior year to final spring · public contributions Apr 2023 - Apr 2024 The owner confirms sustained OpenIM community work from junior year through the final spring; a public retrospective records a six-month internship within that period, while exact employment dates remain pending. Currently ranked first on GitHub's contributor graph, with work across deployment, test automation, protocol and documentation clarification, and the Chinese community. ## Selected Systems ### [DayPage](https://github.com/getyak/daypage) | Internal dogfood · TestFlight v0.4.74 Lightweight capture is compiled by an LLM into a personal knowledge network; next layer: user-defined Skills → agent execution → artifacts returned to the UI. - Public automation delivered TestFlight v0.4.74, with the matching prerelease providing a signed distribution IPA under a fixed SHA-256; nine scheduled regressions succeeded from 22 to 30 Jul 2026, with the latest completing 187 XCTest, 277 Swift Testing tests with 4 known issues recorded by the test framework, and 4/4 Maestro UI flows. - Implemented up to seven-day backfill; Local-to-iCloud vault migration checks file counts and sampled SHA-256 hashes before switching, retains the local backup, and is covered by scheduled CI. - The owner's fact card records a local vault spanning about 250 days of Markdown; this is context-corpus scale, not consecutive usage or external-user count. - Artifacts: [DayPage repository](https://github.com/getyak/daypage), [DayPage AGENTS.md](https://github.com/getyak/daypage/blob/main/AGENTS.md), [TestFlight delivery workflow](https://github.com/getyak/daypage/actions/runs/29885113415), [DayPage v0.4.74 signed IPA prerelease](https://github.com/getyak/daypage/releases/tag/v0.4.74), [DayPage scheduled regression 9/9 (30 Jul)](https://github.com/getyak/daypage/actions/runs/30515110520), [DayPage background compilation service](https://github.com/getyak/daypage/blob/56a0cace04f9fdfa0fedcff73736fc943ad291e8/DayPage/Services/BackgroundCompilationService.swift), [DayPage background compilation tests](https://github.com/getyak/daypage/blob/56a0cace04f9fdfa0fedcff73736fc943ad291e8/DayPageTests/BackgroundCompilationServiceTests.swift), [DayPage vault migration service](https://github.com/getyak/daypage/blob/56a0cace04f9fdfa0fedcff73736fc943ad291e8/DayPage/Services/VaultMigrationService.swift), [DayPage vault migration tests](https://github.com/getyak/daypage/blob/56a0cace04f9fdfa0fedcff73736fc943ad291e8/DayPageTests/VaultMigrationServiceTests.swift), DayPage vault corpus statement (owner_attestation) - Boundary / Not Yet Proven: Skills → agent execution → UI artifacts is the next-layer product architecture; public evidence currently proves capture, LLM compilation, graph retrieval, TestFlight delivery and tested safeguards, not external adoption of the full agent loop, real-device background success, crash-free rate, retention or model cost. ### [Agentry](https://github.com/getyak/daypage/tree/main/agentry) | Working prototype A resumable, auditable agent runtime that unifies loops, tools, sessions, policy and multiple transports. - Implemented a bounded agent loop, replayable JSONL sessions, cancellation-aware retries, HTTP and stdio runtime transports, stdio MCP client/server and agent-as-tool primitives. - The pinned public commit contains 191 top-level tests across 17 packages; build, vet, test and the race detector were reproduced at that commit with 63.2% statement coverage. - Artifacts: [Agentry architecture](https://github.com/getyak/daypage/blob/56a0cace04f9fdfa0fedcff73736fc943ad291e8/agentry/README.md), [Agentry source](https://github.com/getyak/daypage/tree/56a0cace04f9fdfa0fedcff73736fc943ad291e8/agentry), [Agentry pinned runtime and test suite](https://github.com/getyak/daypage/tree/56a0cace04f9fdfa0fedcff73736fc943ad291e8/agentry) - Boundary / Not Yet Proven: This remains a prototype inside the DayPage monorepo; repository CI does not run Agentry tests, the CDP browser package is untested, ask approval and sub-agent profiles are not wired into the CLI, and there is no independent release or external adoption evidence. ### [OpenIM](https://github.com/openimsdk/open-im-server) | Past contribution Owned deployment, CI and contributor governance in a large Go IM project; reached #1 on GitHub's contributor graph. - Ranked first on the OpenIM Server default-branch contributor graph with 358 contributions; a public retrospective documents 100+ PRs and 100+ issues. - Representative merged work includes Helm Charts and Helmfile orchestration for 11 services (#1291), API and E2E testing in GitHub Actions (#1359), and the contributor baseline for RFCs, DCO, PR review and releases (#366). - Published eight long-form OpenIM videos from Oct 2023 to Jan 2024; a public-platform snapshot on 20 Jul 2026 records the top three at 4,736, 3,308 and 959 views. - Artifacts: [OpenIM Server contributors](https://github.com/openimsdk/open-im-server/graphs/contributors), [OpenIM pull requests by cubxxw](https://github.com/search?q=org%3Aopenimsdk+is%3Apr+author%3Acubxxw&type=pullrequests), [OpenIM public retrospective](https://cubxxw.com/engineering/posts/openim-open-source-business-journey/), [OpenIM Helm Charts and Helmfile PR #1291](https://github.com/openimsdk/open-im-server/pull/1291), [OpenIM API and E2E CI PR #1359](https://github.com/openimsdk/open-im-server/pull/1359), [OpenIM contributor governance PR #366](https://github.com/openimsdk/open-im-server/pull/366), [OpenIM long-form video reach on Bilibili](https://space.bilibili.com/1233089591), [Representative OpenIM long-form deep-dive video](https://www.bilibili.com/video/BV1ja4y1f7Qz/) - Boundary / Not Yet Proven: The contribution count does not imply every commit was core IM server code; the resume separates engineering, documentation and community scope. ### [Telepace AI](https://github.com/telepace) | Paused Led an AI feedback analysis SaaS spanning asynchronous data pipelines, real-time web interaction and Kubernetes deployment. - Led the core backend, system integration and deployment while collaborating on the web product; without reaching a first paying user, the initial venture stopped after 28 Oct 2025. - Turned the failure into explicit validation-first sequencing: a later public strategy sets gates of at least 100 signups or 20 paid preorders per concept within three weeks, and a pivot if a direction misses $2K MRR by month four. These are forward-looking kill criteria, not achieved results. - Artifacts: [Telepace GitHub organization](https://github.com/telepace), [Telepace public repository activity](https://github.com/orgs/telepace/repositories), Telepace owner statement (self-attested) (owner_retrospective), [2026 product validation and kill-criteria strategy](https://cubxxw.com/zh/growth/posts/super-individual-ai-product-and-solo-builder-stack/) - Boundary / Not Yet Proven: Paused refers only to the 2024 to 2025 initial venture. The 2026 prototype is listed separately; interview and trial counts still require owner confirmation. **[Public Work Graph](https://cubxxw.com/projects/)**: Products / Prototypes / Engineering Logs _Statuses on product pages are editorial snapshots; delivery and adoption claims remain governed by this resume's evidence layer._ ## Core Stack - **Agent Systems**: Agent loop, MCP, Tool policy, Session lifecycle, Computer Use, Provider abstraction - **Product Systems**: Native iOS, Web, Backend, TestFlight, Local-first - **Validation**: Regression testing, XCTest / Swift Testing, Maestro, Go race detector, CI/CD, Artifact verification - **Languages**: Swift, TypeScript, Go, Python ## Education Wuhan College of Arts & Sciences | Computer Science · undergraduate studies completed | 2024 _Last verified: 2026-08-04_