AI Developer Tool / Memory / Agent Infrastructure
Open-source shared memory layer for multi-agent systems, built around signed, cite-able facts that can be read without an account and integrated via MCP, Python, TypeScript, or REST.
The page clearly presents an AI-focused developer tool with a concrete purpose: persistent shared memory for multi-agent systems. The snapshot shows enough usage evidence for a public listing, including MCP setup, Python and TypeScript install commands, REST access, and example guidance for agents. It also explains the core idea of signed, content-addressed facts and why it exists, making the project understandable and useful to AI builders.
The snapshot gives strong positioning and integration snippets, but it does not show full API reference, setup flow, or a worked end-to-end example of writing and later resolving facts. Visitors also cannot tell from this page alone how mature the project is in production or what reliability limits apply.
Last evaluated 33 days ago. Current rank #471. Up 2 spots in the rankings.
A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.
Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents. It connects files, databases, vector stores, APIs, and MCP tools through one backend with auth, observability, and governance features.
A Claude Code skill that lets the model inspect live camera frames so it can verify hardware displays, spot wiring issues, and check physical UI behavior on real devices.
Runtime safety net for LLM agents that detects runaway token growth, classifies failure patterns, and suggests fixes without extra LLM calls. The project includes a Rust core, Python SDK, examples, benchmarks, and benchmark claims across multiple models and runs.
