PUBLISHED AI RESEARCH AND PROJECTS

AI research and projects

The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.

Clear all filters

A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗

Showing 161–176 of 241 proofs of work · Kind: implementation · Newest first
Page 11 of 16
implementationChecked Sep 20, 2026

Serverless Function Calling Middleware for Conversational Commerce

Raúl Pineda Mejía · Codebridge Tech / The Interactive Studio

Developed a serverless middleware connecting natural language user intents to live inventory databases, executing secure database lookups and payment checkouts via strict JSON schema validation.

Scope & limitations

Requires deterministic database transaction rollbacks if client connection drops during checkout execution.

Context: AWS Lambda, Claude 3.5 Sonnet Tool Use API, PostgreSQL RDS.

View mission
implementationChecked Sep 20, 2026

Serverless High-Throughput vLLM Inference Container Orchestration on Modal

Charles Frye · Modal Labs

Engineered containerized serverless LLM deployment architectures on Modal, orchestrating multi-GPU vLLM inference with cold-start mitigation, dynamic batching, and automated autoscaling from 0 to 100 NVIDIA A100/H100 instances.

Scope & limitations

Cold-start container image pulling and model weight downloading require warm snapshot caching techniques to maintain sub-second response readiness.

Context: Modal Python SDK, CUDA 12, PagedAttention, Tensor Parallelism across NVLink clusters.

View mission
implementationChecked Sep 20, 2026

V-JEPA: Self-Supervised Video Representation Learning by Joint Embedding Prediction

Dr. Yann LeCun · Meta / New York University

Co-authored the implementation and empirical validation of V-JEPA, training Vision Transformers on masked spatiotemporal video tubes using feature-space prediction without pixel reconstruction or data augmentation, achieving superior efficiency on downstream motion and action classification.

Scope & limitations

Requires extensive video pre-training compute (hundreds of GPU-days); does not directly produce human-interpretable generative video frames.

Context: Vision Transformer (ViT-H/16) trained on 2M video clips using 3D masking strategies and EMA target encoder.

View mission
implementationChecked Sep 20, 2026

Fastai Deep Learning Framework and Layered API

Jeremy Howard · Answer.ai / fast.ai

A layered high-level and low-level deep learning library built on top of PyTorch that drastically democratizes state-of-the-art computer vision, NLP, and tabular models with decoupled optimizer and scheduler primitives.

Scope & limitations

Designed primarily for PyTorch ecosystem; high-level abstractions require delving into mid-level API for highly custom multi-modal tensor graphs.

Context: PyTorch 2.4, CUDA 12, mixed-precision FP16/BF16 training, One-Cycle learning rate policies.

View mission
implementationChecked Sep 20, 2026

AI Productivity Hub: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Goda Go · AI Productivity Hub

A verified production automation architecture implemented by Goda Go at AI Productivity Hub, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

AI Sales Training: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Christopher Gallagher · AI Sales Training

A verified production automation architecture implemented by Christopher Gallagher at AI Sales Training, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

AIPRM: High-Throughput Model Serving & Inference Optimization Pipeline

Tibor Blaho · AIPRM

An infrastructure blueprint engineered by Tibor Blaho at AIPRM, implementing dynamic batching, quantized weights, and horizontal autoscaling for high-concurrency model deployment.

Scope & limitations

Deployment specifications are designed for dedicated cloud container environments; cold start latencies must be managed.

Context: Optimized for high-throughput PyTorch / vLLM runtime serving with CUDA acceleration.

View mission
implementationChecked Sep 20, 2026

Alexandria Hamilton Consulting: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Alexandria (Lex) Hamilton · Alexandria Hamilton Consulting

A verified production automation architecture implemented by Alexandria (Lex) Hamilton at Alexandria Hamilton Consulting, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

Autonomous Task Allocation and Priority Rebalancing in BabyAGI

Yohei Nakajima · Untapped VC

A technical case study by Yohei Nakajima detailing how autonomous agent memory structures and vector lookups dynamically rebalance task priority queues based on intermediary tool feedback.

Scope & limitations

Autonomous task loops require strict execution timeout boundaries and token budget quotas.

Context: Python agent loop utilizing LangChain and ChromaDB for episodic memory persistence.

View mission
implementationChecked Sep 20, 2026

BuiltByOU / Clawable.ai: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Misbah Syed · BuiltByOU / Clawable.ai

A verified production automation architecture implemented by Misbah Syed at BuiltByOU / Clawable.ai, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

Certainty Lab: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Danni Zaks · Certainty Lab

A verified production automation architecture implemented by Danni Zaks at Certainty Lab, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

ChatSMB: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Matt Ham · ChatSMB

A verified production automation architecture implemented by Matt Ham at ChatSMB, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

Forward Deployed HQ: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Dhruv Bhatia · Forward Deployed HQ

A verified production automation architecture implemented by Dhruv Bhatia at Forward Deployed HQ, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

GT70 Digital: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Marcelo Tavares · GT70 Digital

A verified production automation architecture implemented by Marcelo Tavares at GT70 Digital, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

HelloHorizon Ltd: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Douglas Cockburn · HelloHorizon Ltd

A verified production automation architecture implemented by Douglas Cockburn at HelloHorizon Ltd, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
implementationChecked Sep 20, 2026

Independent / blog.rezvov.com: Multi-Step Agentic Workflow & Autonomous Error Recovery Engine

Alex Rezvov · Independent / blog.rezvov.com

A verified production automation architecture implemented by Alex Rezvov at Independent / blog.rezvov.com, featuring stateful tool orchestration, automated failure recovery, and structured human approval checkpoints.

Scope & limitations

Operational workflow system; requires monitored execution runtimes and rate-limit backoff handling.

Context: Orchestrated via stateful multi-step agent graphs and deterministic JSON schema validation.

View mission
Showing 161–176 of 241 proofs of work