specstoryai/getspecstory

Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reusable skills with Lore. Sync your conversations to the cloud. File issues and requests.

What it solves

SpecStory prevents the loss of critical architectural decisions, code snippets, and solutions that occur during AI-assisted development. It solves the problem of fragmented context where valuable interactions with AI coding assistants are scattered across different tools, projects, and machines, making them difficult to search or share.

How it works

SpecStory uses a local-first approach to capture and index AI interactions. It provides IDE extensions (for Cursor and VS Code Copilot) and a CLI wrapper that integrates with various AI agents (such as Claude Code, Gemini CLI, and DeepSeek TUI). These tools automatically save every interaction to a .specstory/history/ folder within the project. Users can then optionally sync this data to a cloud platform for global search and sharing, or use the "Lore" tool to mine these local histories into evidence-backed agent skills.

Who it’s for

Developers who use AI coding assistants and want to maintain a searchable, persistent knowledge base of their AI-driven development process across multiple projects and tools.

Highlights

  • Local-First Privacy: All sessions are saved locally by default; cloud sync is an explicit opt-in.
  • Broad Integration: Supports a wide array of tools including Cursor, GitHub Copilot, Claude Code, and various other CLI agents.
  • Lore Skill Mining: Converts actual historical interaction data into reusable agent skills based on how the user actually works.
  • Centralized Knowledge: Offers a cloud platform for full-text search across all projects and programmatic API access.

Related

  • Project
    MoizIbnYousaf/ai-agent-skills

    AI Agent Skills is an npm‑based CLI/TUI that ships a curated library of ~115 AI‑agent “skills” (prompt‑code bundles) organized into shelves (frontend, backend, mobile, workflow, agent‑engineering, marketing). It lets you browse, search, install, and manage both local “house‑copy” skills and upstream metadata‑only skills. You can also bootstrap a personal library with `init-library`, add or catalog new skills, vendor copies, sync updates, and generate documentation. Works with any Agent‑Skills‑compatible agent (Claude, Cursor, Gemini, etc.) and supports multiple install targets. Ideal for developers or teams who want a tidy, searchable toolbox of reusable agent capabilities.

  • Project
    0xSero/ai-data-extraction

    A toolkit for extracting chat history, code context, and diffs from AI coding assistants to create datasets for machine learning training.

  • Project
    supermemoryai/supermemory

    Supermemory is a hosted‑plus‑self‑hostable memory and context engine for LLM‑based assistants. It extracts facts from chats, emails, PDFs, images, code, etc., builds per‑user profiles (static facts + dynamic recent context), and provides hybrid RAG + memory search through a single API (`add`, `profile`, `search`). Plugins let popular tools (Claude Code, Cursor, Codex) gain persistent memory, while a one‑binary `supermemory local` server lets you run the whole stack offline with local embeddings. The project claims state‑of‑the‑art performance on LongMemEval, LoCoMo and ConvoMem benchmarks (95 % Recall@15 with >99 % context reduction).

  • Dispatch
    Managing AI Agent Skills: Community Practices, Tooling, and Version Control Strategies

    Developers organize, version, and test AI agent skill files using git repos, symlinks, custom installers, and evaluation scripts to keep skills reliable and shareable.

  • 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.