memvid

BAMLby BoundaryML

A simple prompting language for building reliable AI workflows and agents. BAML's compiler is written in Rust!

baml0.221.05.1k/90d updated today

montyby pydantic

A minimal, secure Python interpreter for running LLM-generated code in AI agents, with microsecond startup, strict sandboxing, and snapshotting support

monty1.2.098.3k/90d updated today

vestigeby samvallad33

Causal proof engine and operating system for AI agents built on Strata, an append-only signed log. No vectors and no RAG. Every answer carries its proof as a memory id, an edge path or a receipt, and it traces a failure back to the commit that caused it

v5.0.0updated today

entrolyby juyterman1000

Information-theoretic Context Engineering Engine that uses reinforcement learning to intelligently prune and select optimal RAG fragments.

entroly-v1.0.87Pythonupdated 2d ago

Cortex Memoryby sopaco

A complete solution for agent memory, from extraction and vector search to automated optimization, and insights dashboard out-of-the-box.

2.7.1updated 3mo ago

pondby tenequm

Lossless storage and search for AI agent sessions across twelve coding-agent clients, built on Lance over a local directory or an S3 bucket, with BM25 and optional vector retrieval exposed over CLI, HTTP, MCP and read-only SQL

pond-db0.20.1763/90d updated 6d ago

tokio-prompt-orchestratorby Mattbusel

Tokio pipeline for serving LLM requests with dedup, circuit breakers, retries, rate limits and a dead-letter queue in front of Anthropic, OpenAI, llama.cpp or vLLM.

tokio-prompt-orchestrator2.0.4118/90d updated 1d ago