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.

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

Showing 161–176 of 567 proofs of work · Newest first
Page 11 of 36
explanationChecked Sep 22, 2026

Astra Head-to-Head with Fable 5.1: Putting OpenAI's True AGI Claims to the Test

Ed Donner · Ed Donner AI / Independent Advisory

Delivered comprehensive architectural walkthrough detailing enterprise latency SLAs, token economics, fallback routing, and validation layers for financial services.

Scope & limitations

Financial services data governance requires rigorous PII scrubbing before sending payloads to cloud LLMs.

Context: GPT-4o, Claude 3.5 Sonnet, AWS Bedrock, enterprise VPC security.

View mission
implementationChecked Sep 22, 2026

AutoGen and Semantic Kernel Enterprise Blueprints

Cole Medin · Cole Medin AI / Tech Advisory

Maintains open-source codebases demonstrating production patterns for multi-agent software engineering, autonomous research, and dynamic tool orchestration.

Scope & limitations

Complex multi-agent graphs require distributed tracing telemetry (e.g. OpenTelemetry) for production debugging.

Context: Python, AutoGen, Qdrant vector database, LiteLLM proxy.

View mission
implementationChecked Sep 22, 2026

AutoGPT Forge and Benchmark Protocol for Standardized Agent Evaluation

Toran Bruce Richards · Significant Gravitas / AutoGPT

Engineered the AutoGPT Forge and benchmark suite establishing standardized unit tests and reproducible scoring for autonomous agents completing real web navigation and code execution tasks.

Scope & limitations

Complex multi-modal benchmarks require cloud container orchestrators to manage concurrent agent tests.

Context: Agent protocol, CI/CD automated grading, isolated virtual environments.

View mission
implementationChecked Sep 22, 2026

AutoGPT: Autonomous Multi-Step General AI Agent Framework

Toran Bruce Richards · Significant Gravitas / AutoGPT

Created the groundbreaking open-source agent framework featuring goal decomposition, automated internet browsing, long-term memory retrieval, and recursive execution loops.

Scope & limitations

Early unconstrained autonomous loops suffered from loop divergence without strict benchmark rubrics.

Context: GPT-4, LangChain, Pinecone memory, Docker sandbox, Python.

View mission
implementationChecked Sep 22, 2026

Autonomous Agent Architectures and Workflow Templates

Matthew Berman · Forward Future

Maintains open-source implementation guides demonstrating multi-agent routing, tool calling, and structured output parsing with CrewAI, AutoGen, and LangChain.

Scope & limitations

Multi-agent coordination requires strict token budget controls to prevent runaways on recursive self-refinement.

Context: CrewAI multi-agent swarms, Python tool calling, SQLite persistence.

View mission
explanationChecked Sep 22, 2026

Autonomous Procurement and Digital Supply Chain AI Transformation

Dr. Marcell Vollmer · Prospance Inc. / Former SAP CDO

Published research detailing how process mining and generative AI automate invoice processing, contract compliance, supplier negotiations, and fraud detection in Fortune 500 supply chains.

Scope & limitations

Legacy ERP database schemas require custom middleware translation to support LLM structured ingestion.

Context: ERP integrations (SAP, Oracle), Celonis process mining, LLM contract extraction.

View mission
explanationChecked Sep 22, 2026

Autonomous Software Engineering and Frontier Safety Evaluation Metrics

Michael Spencer · AI Explained

Formulated comparative methodology for auditing agentic code generation harnesses against real-world GitHub issues, isolating scaffolding efficacy from raw model intelligence.

Scope & limitations

Unit test pass rates on narrow issue fixes do not evaluate entire codebase architectural coherence.

Context: SWE-bench test harness, Docker execution sandboxes, Claude 3.5 Sonnet.

View mission
implementationChecked Sep 22, 2026

Awesome AI Tools and Local Multimodal Prototyping Harnesses

Alex Volkov · ThursdAI / Synthedia

Built open-source developer prototypes integrating real-time voice, vision harnesses, and local browser automation pipelines to evaluate multi-modal agent latency in production environments.

Scope & limitations

Real-time bidirectional audio requires dedicated edge GPU infrastructure to achieve sub-500ms latency.

Context: WebRTC audio streaming, Whisper.cpp, local Ollama endpoints, LangChain.

View mission
implementationChecked Sep 22, 2026

Awesome LLM Apps: Open Source Production AI Templates

Shubham Saboo · Independent AI Author & Consultant

Maintains an open-source repository of applied AI applications with over 10,000 stars, covering multimodal agents, meeting summarizers, and local offline RAG assistants.

Scope & limitations

Streamlit UI is optimized for internal prototyping rather than high-concurrency consumer apps.

Context: Streamlit, FastAPI, Ollama, LangChain, Phidata agent harnesses.

View mission
researchChecked Sep 22, 2026

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression

Dr. Ji Lin · NVIDIA / MIT

Authored the MLSys 2024 Best Paper introducing AWQ, demonstrating that protecting the top 1% salient weight channels based on activation magnitudes avoids backpropagation retraining and achieves lossless 4-bit inference.

Scope & limitations

Extreme 2-bit quantization still requires second-order error compensation beyond magnitude scaling.

Context: W4A16 GEMM kernels, LLaMA, Mistral, CodeLlama, NVIDIA TensorRT-LLM and vLLM runtimes.

View mission
researchChecked Sep 22, 2026

Benchmarking Vision-Language Models on Live Web Interaction

Gregor Zunic · Browser-Use

Conducted empirical benchmarks assessing vision versus accessibility-tree DOM representation for autonomous agents, proving multimodal screenshot parsing reduces failure rates by 35% on checkout flows.

Scope & limitations

High resolution screenshot ingestion increases token consumption significantly per navigation step.

Context: Claude 3.5 Sonnet vision, WebVoyager benchmark dataset, automated browser sessions.

View mission
researchChecked Sep 22, 2026

Benchmarking Web Extraction Quality for Large Language Models

Minh Do · Crawl4AI

Conducted empirical benchmarks demonstrating a 6x speedup and 70% reduction in context token waste by stripping non-semantic DOM elements prior to RAG embedding.

Scope & limitations

Complex nested web tables with multiple header levels require custom parsing logic.

Context: DOM pruning algorithms, cosine similarity RAG retrieval, token economics.

View mission
researchChecked Sep 22, 2026

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Dr. Thomas Wolf · Hugging Face

Initiated and directed the BigScience open scientific collaboration of 1,000+ researchers, pre-training BLOOM on the Jean Zay supercomputer across 46 natural languages and 13 programming languages.

Scope & limitations

Massive parameter size requires distributed multi-node hardware (8x A100 80GB minimum) for unquantized inference.

Context: 176B parameters, Megatron-DeepSpeed 3D parallelism, ALiBi positional embeddings.

View mission
implementationChecked Sep 22, 2026

Browser-Use: Open-Source AI Agent Web Navigation Engine

Gregor Zunic · Browser-Use

Engineered Browser-Use, a Python library enabling LLMs to interact with web pages through coordinate clicking, typing, scrolling, and DOM element tree inspection using Playwright.

Scope & limitations

Dynamic single-page applications with obfuscated shadow DOMs can occasionally degrade element identification accuracy.

Context: GPT-4o vision, Claude 3.5 Sonnet, Playwright browser automation, JSON action schema.

View mission
explanationChecked Sep 22, 2026

Build Anything with Jev, Here’s How

David Ondrej · Prompt Engineering / Ondrej AI

Constructed and benchmarked cooperative multi-agent architectures that divide research, code synthesis, testing, and documentation across specialized role-based models.

Scope & limitations

Inter-agent communication drift can cause repetitive conversation loops without strict supervisor termination conditions.

Context: AutoGen, CrewAI, GPT-4o, Claude 3.5 Sonnet, local LLaMA-3 models.

View mission
explanationChecked Sep 22, 2026

Building and Scaling an Applied AI Consulting Agency

Dave Ebbelaar · Datalumina / Independent AI Agency

Trained over 5,000 software engineers and consultants on scoping, pricing, and delivering real enterprise AI projects with deterministic acceptance criteria and verifiable ROI.

Scope & limitations

Client proprietary data compliance (GDPR/HIPAA) limits usage of non-EU cloud model APIs.

Context: Enterprise client delivery frameworks, SLA definition for stochastic models.

View mission
Showing 161–176 of 567 proofs of work