nicknisi/sessions — Search and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi.

Description and use

nicknisi/sessions provides a unified, searchable index for AI coding sessions across Claude Code, Codex, and Pi, letting developers fuzzy‑find, resume work from the CLI, give agents persistent memory via MCP, and generate usage reports. Its value lies in standardizing AI‑tool integrations through the Model Context Protocol, offering a clear adoption path: expose the CLI/SDK, run an MCP server, and plug agents into existing workflows with minimal setup. With recent activity, strong ecosystem signals, and a TypeScript‑based implementation, the project shows high production readiness suitable for a serious pilot, pending final license and security review.

Problem

nicknisi/sessions 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

Search and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi. Fuzzy-find and resume from the CLI, give agents recall via MCP, and get usage reports.

Source