| Agentic Workbench |
https://github.com/internal-ref/agentic-workbench |
tool |
integrated |
Agentic Workbench |
Canonical documentation for agentic workbench architectures and human-in-the-loop multi-agent collaboration. |
| Architecture Index |
https://github.com/internal-ref/architecture-index |
tool |
integrated |
Architecture Index |
Referenced in Related section of docs/tools/development_ops/claude-context-mode.md. |
| Azure AI Search |
https://github.com/internal-ref/azure-ai-search |
tool |
integrated |
Azure AI Search |
Canonical page for Azure AI Search vector database and hybrid retrieval platform. |
| GPT-5.5 |
https://github.com/internal-ref/gpt-5-5 |
tool |
integrated |
OpenAI |
Referenced in Related section of docs/tools/orchestration/apache-airflow.md. |
| Gemma |
https://github.com/internal-ref/gemma |
tool |
integrated |
Gemma |
Referenced in Related section of docs/tools/ai_knowledge/heretic-ara.md. |
| Gemma 3 |
https://github.com/internal-ref/gemma-3 |
tool |
integrated |
Gemma |
Standard open weights foundation model integrated into canonical Gemma documentation. |
| Google AI Studio |
https://github.com/internal-ref/google-ai-studio |
tool |
integrated |
Google AI Studio |
Web sandbox and API developer portal for Gemini and Gemma models. |
| Grok-3 |
https://github.com/internal-ref/grok-3 |
tool |
integrated |
xAI Grok |
Flagship reasoning engine integrated into xAI Grok canonical documentation. |
| Inspect AI |
https://github.com/internal-ref/inspect-ai |
tool |
integrated |
Inspect AI |
Framework by UK AISI for orchestrating model evaluations and safety benchmarks. |
| Lama 4 Maverick |
https://github.com/internal-ref/lama-4-maverick |
tool |
integrated |
Llama 4 Maverick |
High-capacity fine-tuned agentic model variant in Meta Llama 4 family. |
| Llama |
https://github.com/internal-ref/llama |
tool |
integrated |
Llama |
Meta open-weights foundation model family lineage and architecture overview. |
| Llama 4 |
https://github.com/internal-ref/llama-4 |
tool |
integrated |
Llama 4 |
Next-generation sparse Mixture-of-Experts open foundation model family. |
| Logfire |
https://github.com/internal-ref/logfire |
tool |
integrated |
Logfire |
Pydantic observability, tracing, and logging platform for Python/LLM apps. |
| Loki |
https://github.com/internal-ref/loki |
tool |
integrated |
Grafana Loki |
Scalable log aggregation system indexing metadata labels for Grafana LGTM stack. |
| MkDocs |
https://github.com/internal-ref/mkdocs |
tool |
integrated |
tools/development_ops/mkdocs.md |
MkDocs static site generator |
| Multi-Agent Systems |
https://github.com/internal-ref/multi-agent-systems |
tool |
integrated |
tools/agents/multi-agent-systems.md |
Multi-agent orchestration paradigm and topologies |
| MultiPL-E |
https://github.com/internal-ref/multipl-e |
tool |
integrated |
tools/benchmarking/multipl-e.md |
Polyglot code generation benchmark suite |
| Okta |
https://github.com/internal-ref/okta |
tool |
integrated |
tools/enterprise/okta.md |
Cloud enterprise identity and access management platform |
| PEFT |
https://github.com/internal-ref/peft |
tool |
integrated |
tools/infrastructure/peft.md |
Hugging Face Parameter-Efficient Fine-Tuning library |
| Prometheus |
https://github.com/internal-ref/prometheus |
tool |
integrated |
Prometheus |
Open-source metrics collection, PromQL query engine, and time-series monitoring. |
| Proton Mail |
https://github.com/internal-ref/proton-mail |
tool |
integrated |
Proton Mail |
End-to-end encrypted email service and Proton Mail Bridge IMAP/SMTP integration. |
| Qdrant |
https://github.com/internal-ref/qdrant |
tool |
integrated |
Qdrant |
High-performance Rust vector database with HNSW graph indexing and payload filtering. |
| Sandboxed Code Execution |
https://github.com/internal-ref/sandboxed-code-execution |
tool |
integrated |
Sandboxed Code Execution |
Design pattern for isolated container and microVM execution of untrusted code. |
| System Prompt Engineering |
https://github.com/internal-ref/system-prompt-engineering |
tool |
integrated |
System Prompt Engineering |
Methodology for steering LLM reasoning, safety guardrails, and tool formatting. |
| Tempo |
https://github.com/internal-ref/tempo |
tool |
integrated |
Tempo |
Object-storage distributed tracing backend for OpenTelemetry and Grafana LGTM. |
| TensorRT-LLM |
https://github.com/internal-ref/tensorrt-llm |
tool |
integrated |
TensorRT-LLM |
NVIDIA library for compiled high-throughput, low-latency GPU LLM inference. |
| Triton |
https://github.com/internal-ref/triton |
tool |
integrated |
Triton |
Pythonic GPU kernel programming language and compiler for high-performance AI. |