Prysai · Selected work · Working set · Star history
RUIMING ZHAO · UZZRM
I build and inspect AI systems that hold up beyond the demo: agents, retrieval, evaluation, and tool use in real developer workflows.
The standard is simple: fewer impressive demos, more systems that can be tested, understood, and improved. WORKING FOCUS
AI agents
Developer tools
Reliable delivery
Network operations · independent development · image-model training and fine-tuning
I build and inspect AI systems that hold up beyond the demo: agents, retrieval, evaluation, and tool use in real developer workflows.
The standard is simple: fewer impressive demos, more systems that can be tested, understood, and improved. WORKING FOCUS
AI agents
Developer tools
Reliable delivery
Network operations · independent development · image-model training and fine-tuning
Six years in network operations and four years as an independent developer inform the work. Since 2024, this has also included full-quantization training and fine-tuning workflows for image AI models.
Python TypeScript C Sharp Go JavaScript Rust C Plus Plus C Java R Scala Svelte HTML CSS Shell PowerShell Docker CMake
Languages and platforms represented in public projects or accepted upstream work. This is evidence of practical exposure and collaboration, not a claim of equal depth in every language.
AI agents LLM evaluation Model Context Protocol RAG systems Agent reliability Security redaction Test engineering Image model training
GitHub followers On GitHub since March 2026 Account star history refreshed daily
Prysai website Prysai LLM Playbook documentation Prysai LLM Playbook GitHub stars Prysai LLM Playbook v0.1.0-alpha release Prysai on Hugging Face
Follower and Playbook-star badges update from their public sources. Every badge links to its public source.
PUBLIC FLAGSHIP
Prysai LLM
Playbook An evidence-led, six-language learning and practice system for reliable work with LLMs, Codex, skills, tools, and agent workflows.
repository · documentation · v0.1.0-alpha
Public development candidate. Structure and checks are inspectable; learner validation and independent review remain in progress.
Prysai LLM
Playbook An evidence-led, six-language learning and practice system for reliable work with LLMs, Codex, skills, tools, and agent workflows.
repository · documentation · v0.1.0-alpha
Public development candidate. Structure and checks are inspectable; learner validation and independent review remain in progress.
A curated, evidence-first record of changes accepted into other projects. The full directory stays available below.
AGENT RUNTIME
Microsoft Agent Framework
Telemetry configuration, skill-script behavior, prompt-cache usage, and operational visibility.
latest merged PR RELIABILITY
corecoder-ts
Cancellation, timeouts, context accounting, protocol edge cases, and CLI contracts.
latest merged PR
Microsoft Agent Framework
Telemetry configuration, skill-script behavior, prompt-cache usage, and operational visibility.
latest merged PR RELIABILITY
corecoder-ts
Cancellation, timeouts, context accounting, protocol edge cases, and CLI contracts.
latest merged PR
SAFETY & OPERATIONS
Open Connector
Connector lifecycle support and redaction that keeps credentials out of run logs.
latest merged PR LANGUAGE ANALYSIS
GitGalaxy
Parser correctness across TypeScript, C#, C++, and Go edge cases.
latest merged PR
Open Connector
Connector lifecycle support and redaction that keeps credentials out of run logs.
latest merged PR LANGUAGE ANALYSIS
GitGalaxy
Parser correctness across TypeScript, C#, C++, and Go edge cases.
latest merged PR
Browse the complete merged contribution directory
| Proof of work |
|---|
| COLLABORATION & TEST RELIABILITY jupyterlab/jupyter-chat · PR #521 · #486 · merged Eliminated SQLite YStore lock contention in parallel UI tests, then made internal chat ID and timestamp mutations synchronous while retaining observer delivery without background-task leakage. |
| AGENT RUNTIME & OPERATIONS microsoft/agent-framework · PR #7695 · #7625 · #7622 · #7597 · merged Made rejected MCP skill archives visible at the operational warning level, preserved Mistral prompt-cache usage details, clarified supported skill-script arguments, and forwarded GitHub Copilot telemetry configuration to its CLI client. |
| AGENT CLI & INTEGRATION gnt-ai/gnt · PR #183 · #182 · #178 · #177 · #176 · #175 · #174 · #173 · #172 · #168 · #164 · #163 · #162 · #138 · merged Expanded CLI automation with JSON output and connector coverage; added guarded Cline and OpenAI Agents SDK integrations; and strengthened terminal formatting, repository conventions, documentation, and review output. |
| ROUTING & OBSERVABILITY vllm-project/semantic-router · PR #2907 · #2896 · #2874 · merged Corrected Router Replay attribution, wired configured Milvus consistency through cache reads and collection setup, and removed a racy Dashboard assertion while retaining stable lifecycle guarantees. |
| VOICE AI & CONFIGURATION livekit/agents · PR #6866 · #6810 · merged Added explicit Google Speech-to-Text project selection while preserving credential-based discovery, and corrected the final sentence span so tokenization includes the input's last character. |
| CONNECTORS & PRODUCT INTEGRATION oomol-lab/open-connector · PR #342 · #332 · #300 · merged Expanded the Resend connector from basic sending into batch, scheduling, retrieval, cancellation, and attachment workflows; made run-log summaries resilient to malformed values; and redacted credentials in protocol-relative and non-HTTP URLs. |
| VOICE AI & AUDIO PIPELINES pipecat-ai/pipecat · PR #5298 · merged Made AssemblyAI speech recognition inherit the pipeline input sample rate unless callers provide an explicit override. |
| EVALUATION & OBSERVABILITY thangldw/ragops · PR #30 · merged Added an offline Phoenix recorded-score adapter with deterministic case-ID joins, synthetic fixtures, documentation, and tests. |
| AGENT TOOLING & COMPATIBILITY ag2ai/ag2 · PR #3160 · #3148 · merged Added HEIC and HEIF MIME types to the Gemini image-input path, and made persistent sub-agent delegation reuse one stream instance so its turn lock actually serializes concurrent work. |
| AGENT TOOLING & COMPATIBILITY mlflow/mlflow · PR #25010 · #25000 · merged Preserved provider-specific usage metadata across Gemini, Anthropic, and OpenAI-compatible gateway adapters, with regression coverage for normalized and nested usage details. |
| AGENT TOOLING & DOCUMENTATION jupyterlab/jupyter-ai · PR #1639 · merged Added a concise interaction model explaining how chat, personas, ACP agents, model providers, and MCP tools fit together. |
| MEMORY & OPERATIONS MSKazemi/kubeintellect · PR #116 · #111 · #105 · merged Made the memory-recall similarity floor configurable, updated the kube-q Homebrew formula, and documented v4 data-handling boundaries. |
| LANGUAGE ANALYSIS & RELIABILITY squid-protocol/gitgalaxy · PR #1764 · #1761 · #1760 · #1724 · #1710 · #1657 · #1655 · #1654 · #1639 · #1201 · merged Improved detector correctness across TypeScript, C#, C++, and Go: recovered missed bodyless functions, retained unknown macro branches, eliminated phantom matches, recognized readonly/ref structs, and prevented silent archetype-metric dimension truncation. |
| AGENT TOOLING & COMPATIBILITY mastra-ai/mastra · PR #21559 · #21281 · #21147 · merged Kept array text-streams valid for batched first chunks, resolved dynamic models once per assigned-tool batch, and fixed CommonJS schema compatibility by bundling the Zod conversion dependencies. |
| RELIABILITY & EXPERIENCE felladrin/MiniSearch · PR #2390 · #2387 · #2386 · #2385 · #2377 · #2375 · #2372 · #2370 · #2367 · #2339 · #2324 · merged Reworked the search experience with a proper landing page, clearer result hierarchy, and reduced-motion-aware drawers; hardened it end-to-end for IME and non-Latin follow-ups, failure states, early rate limiting, SSRF-safe capped thumbnail fetches, and robust error handling. |
| AGENT ORCHESTRATION & CLI a5c-ai/babysitter · PR #1727 · merged Made process-backed run creation safely adopt the active session-start bare run while retaining explicit-run and cross-boundary create-new safeguards. |
| AGENT RUNTIME & RELIABILITY nullcache/corecoder-ts · PR #7 · #6 · #5 · #3 · #2 · #1 · merged Hardened agent execution around cancellation, retry aborts, SSE and tool-input edge cases, request timeouts, context calibration, and CLI contracts; also documented installation, providers, tools, and runtime controls. |
| AGENT TOOLING & QUALITY GATES wshobson/agents · PR #662 · merged Made plugin evaluation preserve and resolve nested skill references relative to the current skill, preventing valid helpers from being incorrectly penalized. |
| PRIVACY & EVALUATION seva9523/EvalRepro · PR #12 · merged Added --no-id_preview to suppress sample ID previews while preserving sample and field digests. |
| DOCUMENTATION & DEVELOPER EXPERIENCE abenneto/gandharva · PR #19 · merged Refined README formatting and section headers. |
Every entry above links to a public pull request confirmed as merged into its upstream repository.
A focused upstream working set. These are study and contribution paths, not claims of original ownership.
RAGOps
Evaluation infrastructure
Offline evaluation and explainable release gates for RAG systems and agents.
upstream · my fork PydanticAI
Typed agent runtime
Typed tools, structured outputs, and validation for production-minded agents.
upstream · my fork
Evaluation infrastructure
Offline evaluation and explainable release gates for RAG systems and agents.
upstream · my fork PydanticAI
Typed agent runtime
Typed tools, structured outputs, and validation for production-minded agents.
upstream · my fork
FastMCP
Tool connectivity
Protocol infrastructure for connecting MCP servers and clients.
upstream · my fork Promptfoo
Quality and safety gates
Evaluation and red-teaming for prompts, agents, and RAG pipelines.
upstream · my fork
Tool connectivity
Protocol infrastructure for connecting MCP servers and clients.
upstream · my fork Promptfoo
Quality and safety gates
Evaluation and red-teaming for prompts, agents, and RAG pipelines.
upstream · my fork
Browser Use
Real-world execution
Browser control for tool-using agents and workflow automation.
upstream · my fork Spec Kitty
Developer workflow
Spec-driven development and repeatable worktree workflows for serious projects.
upstream · my fork
Real-world execution
Browser control for tool-using agents and workflow automation.
upstream · my fork Spec Kitty
Developer workflow
Spec-driven development and repeatable worktree workflows for serious projects.
upstream · my fork
One account-level signal: the total stars received by all public repositories over time. It is a trend for the account, not the star count of any single project.
All public repositories are included · forks contribute only their own stars · refreshed daily by GitHub Actions.
AI agents · retrieval · evaluation · MCP · developer tools · reliable workflows