dollspace-gay/chainlink

A CLI issue tracker for AI Agents

What it solves

Chainlink is a local-first issue tracker CLI designed specifically for AI-assisted development. It solves the problem of context loss between AI sessions (such as those with Claude Code or other LLM agents) by providing a persistent memory layer for tasks, handoff notes, and coding standards.

How it works

The tool stores all data in a local SQLite database. It allows users to track issues, sub-issues, and dependencies while managing "sessions" that record breadcrumbs and handoff notes to bridge the gap between AI restarts.

It integrates with AI agents through two primary methods:

  1. Native Hooks: Specifically for Claude Code, it injects behavioral guardrails (e.g., "no stubs," "no dead code") and enforces issue tracking via Python scripts.
  2. Context Provider: A script that generates structured context (XML, Markdown, or JSON) containing current session state, open issues, and project-specific coding rules that can be prepended to prompts for any LLM agent (Cursor, Aider, Continue.dev, etc.).

Who it’s for

Developers who use AI coding assistants and want a structured way to track progress, enforce coding standards, and maintain continuity across multiple AI-driven development sessions.

Highlights

  • Session Memory: Uses handoff notes and breadcrumbs to survive context resets and compression.
  • Local-first Storage: All data is kept in a local SQLite database with no external dependencies.
  • AI Guardrails: Injects language-specific best practices and blocks certain git mutations to ensure human-only operations.
  • Agent Agnostic: Provides a context provider to integrate with any AI agent via shell aliases or configuration files.
  • Task Management: Supports issue hierarchies, milestones, time tracking, and dependency blocking.

Related

  • Project
    specstoryai/getspecstory

    A local-first knowledge management system that captures, indexes, and makes searchable all interactions with AI coding assistants across various IDEs and CLI tools.

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based server that records every observation a coding‑assistant makes (prompts, tool calls, session boundaries) as plain markdown files in a git‑backed wiki. The server can be run locally, in Docker/Podman, or on a homelab box and is designed to be shared across many agents (Claude Code, Codex, Cursor, Gemini CLI, etc.), machines and team members. Hooks posted by agents are consolidated into readable wiki pages at session end; the next session receives a concise handoff so it can continue exactly where the previous one stopped. Storage is human‑readable markdown plus a SQLite index (FTS5, entity and optional vector search). By default it needs no LLM or embedding keys; optional Anthropic/OpenAI integrations add LLM‑generated summaries and semantic search. Multi‑user authentication, audit logs and per‑person attribution are built in. Install via Arch AUR, Docker wrapper, or native binary, start the server, register a client and its hooks, and the system works transparently.

  • Project
    JamesShi96/project-butler

    A persistent memory system for AI coding assistants that uses a structured Markdown-based memory stack to maintain project context, rules, and progress across sessions.

  • Project
    FerroxLabs/wayland

    A local-first desktop AI agent command center that orchestrates multiple AI CLIs and agents from one interface with shared persistent memory.

  • Project
    Ancienttwo/repo-harness

    A file-backed workflow and runtime for AI agents that replaces chat memory with repository-local artifacts to ensure continuity and consistency across sessions.