The AI Contract Runtime
-
Updated
Mar 22, 2026 - Python
#
llm-systems
Here are 18 public repositories matching this topic...
A muti-agent Dnd DM that directs you to dive into a fantasy world!
-
Updated
Dec 17, 2025 - Python
Structure-first pipeline that transforms GitHub repositories into question-indexed, graph-grounded semantic assets for code search, Graph-RAG, and LLM-based reasoning.
static-analysis code-analysis code-graph code-understanding research-pipeline semantic-indexing graph-rag graph-based-retrieval llm-systems structure-first
-
Updated
Jan 12, 2026 - Python
Open-source harness distillation: frontier teachers improve prompts, tools, validators, skills, and runtime policies around weaker models.
model-evaluation ai-agents tool-use prompt-engineering small-models llm-systems runtime-policies harness-distillation
-
Updated
Jul 7, 2026 - Python
PromptGuard is a pragmatic, opinionated framework for establishing continuous integration for LLM behavior. It operates on a simple, verifiable principle: run the same prompts across multiple model configurations, compare outputs against defined expectations, and flag semantic regressions.
python nlp open-source developer-tools regression-testing ai-safety mlops llm prompt-engineering prompt-testing llm-evaluation ai-infrastructure model-reliability semantic-drift llm-systems
-
Updated
Jan 17, 2026 - Python
A hands-on technical book and Python lab for building and evaluating agentic systems.
python tracing mlx ai-agents guardrails prompt-injection evals quarto-book agentic-systems llm-systems
-
Updated
Jul 22, 2026 - Python
Prototype for execution-plan-driven data standardization, schema profiling, validation, and preview generation.
python data-validation data-engineering execution-plan schema-detection ai-infrastructure llm-systems
-
Updated
Jun 19, 2026 - Python
A conservative, agentic RAG system with evidence-bounded synthesis, citation enforcement, and zero hallucination tolerance.
rag vector-database qdrant llm retrieval-augmented-generation llm-safety hallucination-mitigation agentic-ai llm-systems
-
Updated
Apr 18, 2026 - Python
Solutions to CMU 11-868 Large Language Model Systems assignments — efficient attention/kernels, memory & quantization optimizations, and parallel training/serving — implemented and CPU-verified
cuda pytorch transformer lora quantization autodiff distributed-training pipeline-parallelism kv-cache csdiy llm-systems cmu-11868
-
Updated
Jul 4, 2026 - Python
Production-grade Retrieval-Augmented Generation (RAG) system for evidence-grounded equity research over SEC filings and live market news.
financial-analysis pinecone sec-filings fastapi vector-database langchain-python genai retrieval-augmented-generation llm-systems
-
Updated
Jul 22, 2026 - Python
Research-grade neuro-symbolic RAG framework where retrieval is a policy, not a vector search, built for evaluation, ablation, and reliability analysis.
information-retrieval semantic-search umap bm25 hierarchical-clustering faiss rag neuro-symbolic ablation-study hybrid-retrieval knowledge-retrieval retrieval-evaluation llm-systems graph-retrieval
-
Updated
Jan 4, 2026 - Python
Reference Python kernel for CIMT: no-meta, observable-only certification machinery for affordance-compiled LLM-integrated systems.
python json-schema formal-methods certification reproducibility reference-implementation receipts schema-first research-software llm-evaluation llm-agents llm-systems observable-only no-meta evidence-ledger affordance-compiled-intelligence cognitive-impedance target-firewall debt-calculus
-
Updated
May 12, 2026 - Python
Explicit control and observability over when an LLM should answer, hedge, or refuse — treating generation as a governed system layer, not a side effect of retrieval.
rag failure-modes ai-observability retrieval-augmented-generation agent-architecture agentic-systems llm-systems hallucination-control refusal-policies
-
Updated
Mar 5, 2026 - Python
Failure-first analysis of retrieval-augmented and agentic systems, focused on isolating and attributing failures across retrieval, planning, execution, memory, and policy layers.
evaluation-framework rag failure-analysis agent-systems ai-observability ml-systems retrieval-augmented-generation system-debug agent-architecture llm-systems
-
Updated
Feb 1, 2026 - Python
A unified, production-grade LLM training and alignment framework. Features modular implementations for downstream tasks BERT, DPO, and GRPO to streamline model alignment and optimize memory overhead.
transformers pytorch rl attention-mechanism from-scratch preference-learning dpo ai-engineering ml-systems llm grpo llm-systems
-
Updated
Jun 3, 2026 - Python
Building reliable LLM knowledge systems with Retrieval-Augmented Generation (RAG), retrieval evaluation, semantic search, and production-oriented AI engineering.
python information-retrieval embeddings semantic-search knowledge-representation rag vector-database ai-engineering llm chromadb retrieval-augmented-generation llm-evaluation llm-systems
-
Updated
Jul 20, 2026 - Python
Portfolio-ready AI research monorepo spanning LLM evaluation, agentic AI, reinforcement learning, recommender systems, multimodal AI, vision, NLP, tabular ML, time series, and MLOps labs.
-
Updated
Apr 7, 2026 - Python
Local-first governed LLM support workflow with signed webhooks, guardrails, human approval, audit trails, cost controls, and deterministic evaluation paths.
redis docker-compose postgresql human-in-the-loop fastapi guardrails ai-observability llm-evaluation llm-systems
-
Updated
Jul 13, 2026 - Python
Improve this page
Add a description, image, and links to the llm-systems topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-systems topic, visit your repo's landing page and select "manage topics."