codependentai/resonant — Open-source relational AI framework with identity persistence, memory, and MCP integration.

Description and use

**Brief Summary (2‑3 sentences)**
codependentai/resonant is an open‑source, relational AI framework that gives agents persistent identity, long‑term memory, and native Model Context Protocol (MCP) integration. Built on the Claude Agent SDK and written in TypeScript, it lets developers create relationship‑aware assistants that can remember past interactions, evolve over time, and seamlessly invoke real‑world tools and data sources.

**Value**

• **Continuity & Personalisation:** Persistent identities and memory let agents maintain context across sessions, enabling more natural, trust‑building conversations.
• **Standardised Tool Access:** By exposing a uniform MCP‑based interface, Resonant removes the “glue code” barrier between LLM agents and external services, accelerating integration of databases, APIs, or UI components.
• **Rapid Prototyping:** The Claude Agent SDK foundation provides high‑level abstractions (agents, tools, prompts) so teams can focus on domain logic rather than low‑level LLM plumbing.

**Practical Adoption Path**

1. **Prototype:** Clone the repo, run the provided CLI/SDK demo, and connect a simple tool (e.g., a weather API) via the MCP server.
2. **Extend:** Define custom agent personas and memory schemas in TypeScript, then register additional tool adapters using the built‑in plugin system.
3. **Integrate:** Deploy the MCP server (Docker or serverless) alongside your existing backend, and point any Claude‑compatible assistant to it via the exposed API endpoint.
4. **Scale:** Replace the in‑memory store with a persistent vector DB (e.g., Pinecone, Weaviate) for production‑grade long‑term memory, and configure load‑balanced MCP instances.

**Production Readiness**

• **Activity & Ecosystem:** Recent commits (as of 2026‑05‑12), 34 GitHub stars, 11 forks, and 19 topical tags indicate an active community.
• **Maturity:** The framework leverages the well‑maintained Claude Agent SDK and follows the emerging Model Context Protocol, both of which are already used in several pilot projects.
• **Readiness Level:** High for an OSS candidate—core features (identity, memory, MCP) are stable, documentation includes API/CLI examples, and the TypeScript codebase is straightforward to audit.
• **Remaining Checks:** Final due‑diligence should verify the project’s license compatibility, security posture (dependency scanning), and the presence of an active maintainer for long‑term support. Once those are cleared, Resonant is suitable for serious pilots or production deployments that require relational AI capabilities.

Problem

codependentai/resonant helps connect AI assistants to real tools and data through a standard protocol.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

Open-source relational AI framework with identity persistence, memory, and MCP integration. Build relationship-aware AI agents that remember, grow, and maintain continuity. Built on Claude Agent SDK.

Source