redevops-io ORG

Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.

Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.

Local coding-agent orchestrator — DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.

Quick demo for regime aware asset allocation based on: https://ora.ox.ac.uk/objects/uuid:1a421d83-a010-484e-83c1-504bc9f1cbbf/files/d7s75dd17x and https://rpc.cfainstitute.org/sites/default/files/docs/research-reports/rf_aiinassetmanagement_full-monograph_online.pdf

Self-demonstrating ReDevOps × AWS deploy-and-operate demo: one prompt in Projects provisions, secures, monitors and self-heals a real EKS stack — governed by Mission Runtime, optimized by Context Runtime.

The control plane for the redevops.io Agentic Business OS — Mission Runtime kernel (Python + Go), Projects cockpit, cost-aware LLM router, permissions plane, and reference apps. Self-hosted, open-core (AGPL-3.0).

Shared agent harness (tools, permissions, evals, guardrails) for redevops.io Agentic Business OS modules. AGPL-3.0.

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

Build Real-Time Knowledge Graphs for AI Agents

ingress-nginx post-decomissioning version

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞