Skip to content
View azank1's full-sized avatar
🧠
🧠

Organizations

@delivery-app-us

Block or report azank1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
azank1/README.md

Software engineer working on AI agents and the systems that check them

Azan Hyder. I turn research questions into working software, with a focus on systems that are measurable, inspectable, and useful beyond the demo.

Website Email GitHub X dev.to


Core focus

Metaorcha — many models, one harness. Building Orcha, an Apache 2.0 runtime where one goal becomes a verified multi-agent run across MCP, A2A, and Computer-Use.

Stage Milestone
🟢 Now v1 runtime: multiprotocol orchestration, shipping locally
🟡 Next v1.2 harness: DAG execution, output verification, retry and fallback
🔵 Aim network layer: peer discovery, fulfillment, reputation

What I build

🤖 AI and agent systems
Agent orchestration, MCP tool ecosystems, retrieval, and verification loops for more dependable model behavior.
🔗 Decentralized systems
Experiments in governance, trust-minimized exchange, zero-knowledge proofs, and fairer economic coordination.
📈 Quantitative research tools
Probabilistic models, backtesting systems, and analysis software that make assumptions visible.

Writing

The Harness Layer on dev.to: research field notes on agent harnesses, each with sources, a limitations section and a reproducible artifact. Latest: When should an agent stop? (artifact in code-desk-cli/research). Practice pieces and short takes on X.


Selected work

Code Desks
Run an office of AI coding sessions from your terminal: two hats, gated handoffs, and a meter that reads what each desk really used.

Python Agents MIT
Code Desks stars Code Desks last commit
Metaorcha · metaorcha.ai
Apache 2.0 runtime for multi-protocol agent orchestration.

Python Agents
Metaorcha stars Metaorcha last commit
CDV
A frozen public research preview for judging AI-agent work with a deterministic floor, an LLM critic, and Bayesian stopping.

Python LLM evaluation
CDV stars CDV license
ML Trend Probability
A machine-learning signal framework that tunes and stacks trading indicators into a trend-probability strategy.

Python ML Quant
ML Trend Probability stars
SDCA RAQQR
A Bitcoin market-risk model and backtesting library for accumulation and distribution strategies.

Python Quant research
SDCA RAQQR stars

Capabilities

Languages and application development

Python TypeScript FastAPI PostgreSQL Redis

AI and data

NumPy scikit-learn TensorFlow LangGraph MCP

Infrastructure and decentralized systems

Docker Google Cloud Supabase Ethereum Solidity

Core languages

Python TypeScript Rust Solidity Shell


Activity


Let's build together

If you are working on agent runtimes, protocol bridges, or verification, open an issue on Metaorcha or send me an email.

"It's all relative."

X @azankhyder · dev.to @azankhyder · Code Desks · metaorcha.ai · Email

Pinned Loading

  1. solvent-labs-org/metaorcha solvent-labs-org/metaorcha Public

    multi model capable single harness orchestrator. Apache 2.0 runtime for multi-protocol agent orchestration: one goal in, a verified multi-agent run out across MCP, A2A, and Computer-Use and whateve…

    Python 5 4

  2. cdv cdv Public

    Conservative Dual-Verify — judging AI agent work with a deterministic floor + LLM critic (stricter score wins) and Bayesian stopping. Research preview, frozen at v1.0.1; active development continue…

    Python 4

  3. ML-ProbabalisticTrend ML-ProbabalisticTrend Public

    Machine Learning Trend Probability Indicator - azank1

    Python 4

  4. sdca-raqqr sdca-raqqr Public

    Bitcoin valuation and DCA backtest library. Implements the RAQQR asymmetric tail-curvature rainbow model to score market risk (0–100) and simulate accumulation/distribution strategies against histo…

    Python 1

  5. zk2p zk2p Public

    ZK-proof settlement research prototype — trust-minimized P2P exchange using zero-knowledge proofs and DKIM-verified attestations. Research/PoC.

    TypeScript

  6. quant-pm quant-pm Public

    A pip-installable CLI + library that uses PERT analysis, Gantt scheduling, and multi-developer workload modeling to produce monthly payout breakdowns, timeline projections, and both static (PNG/Exc…