ctxrs/ctx

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

What it solves

Coding agents often leave behind verbose log files containing decisions, assumptions, and failed attempts that are difficult for both humans and agents to search and retrieve. ctx provides a fast, local way to index and search these transcripts to prevent repeated work, reduce token spend, and recover historical context that is not present in the final code.

How it works

ctx scans local agent history files (such as JSONL or SQLite databases) from various providers like Claude Code, Cursor, and OpenHands. It converts these into consistent local records and indexes them using Tantivy for high-performance lexical search. It also supports local semantic search via embeddings. The "ctx pro" add-on allows users to map specific lines of code, commits, or PRs back to the original agent session that produced them, similar to a git blame for agent sessions.

Who it’s for

Developers using AI coding agents who want to maintain a long-term, non-lossy memory of their agent's work across different sessions and tools.

Highlights

  • Broad Agent Support: Supports a wide array of agent harnesses including Claude Code, Cursor, Codex, and many others.
  • Local-First Privacy: All indexing and search run locally; prompts and transcripts are not sent to cloud services.
  • High Efficiency: Uses Tantivy for indexing, making it significantly faster than traditional database ingestions and more token-efficient than raw transcript search.
  • Provenance Tracking: The pro version enables attribution of code changes to specific agent sessions via ctx blame.
  • Hybrid Search: Combines BM25 lexical matching with local semantic search for more flexible retrieval.

Related

  • Dispatch
    ctx: Local Search for Coding Agent History

    ctx is an open-source Rust-based CLI that indexes local coding agent session logs into SQLite to provide fast, token-efficient retrieval of past decisions and failed attempts.

  • Project
    Dicklesworthstone/coding_agent_session_search

    A Rust‑based terminal UI and CLI that aggregates, normalises, and indexes the conversation logs of dozens of AI coding assistants into a local SQLite archive. It provides sub‑60 ms lexical search and optional on‑device MiniLM semantic search, with a stable JSON robot‑mode API for automation and diagnostics.

  • 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
    mcncarl/agent-memory-vault

    A local-first, Git-backed long-term memory system that allows AI coding agents like Claude Code and Codex to share a shared, verifiable Markdown-based memory vault.

  • Dispatch
    Recall: Local Project Memory for Claude Code

    Recall is an offline, local-first plugin for Claude Code that captures session history and uses a TF-IDF and TextRank summarizer to create durable project memory without spending model tokens.