Tag
Explore by tags
Local-first session analytics for AI coding agents: discover, search, and track token usage and estimated costs across Claude Code, Codex, Forge and 20+ other agents. Single binary / desktop app that runs locally (no cloud accounts) with fast, SQLite-backed queries and optional PostgreSQL/DuckDB sync.
Dramatically reduces AI agents' context usage by sandboxing large tool outputs and indexing only relevant snippets into a searchable SQLite FTS5 (BM25) knowledge base, improving session continuity and privacy. Deploys cross-platform hooks and sandbox tools to cut context size by ~98% and avoid dumping raw logs into the model's window. ([github.com](https://github.com/mksglu/context-mode/blob/main/README.md?utm_source=openai))
Indexes codebases into a persistent, queryable knowledge graph for AI coding agents, enabling full-repo indexing in minutes and sub-millisecond structural queries. Bundles 158 vendored tree-sitter grammars, a Hybrid LSP resolver, built-in embeddings, and 14 MCP tools for search, trace, and architecture analysis.
Provides persistent, searchable memory for coding agents (Claude Code, Cursor, Gemini CLI, etc.), automatically capturing tool usage and session facts. Combines BM25, vector embeddings and a knowledge graph for hybrid retrieval, reducing token costs and re-explaining between sessions.
Orchestrates autonomous coding agents to run isolated implementation tasks end-to-end: spawn runs from project boards that produce CI results, PR review feedback, complexity analysis, and walkthrough videos, and safely land accepted PRs. Experimental engineering preview for trusted environments; best for teams using harness engineering.
Builds a local structural knowledge graph of a codebase so AI coding assistants read only the minimal, relevant code during reviews and daily tasks—reducing tokens used while providing blast-radius impact analysis, incremental updates, and MCP integrations.
Provides AI coding agents with persistent memory inside an Obsidian vault—preserving session context, decisions, and notes across sessions. Integrates hooks/commands for Claude Code, Codex CLI, and Gemini CLI and optionally uses QMD for semantic recall; aimed at developer workflows.
Provides a rule set and agent skill that lets AI coding assistants review and improve SwiftUI code for modern APIs, performance, accessibility, and maintainability. Packs checks for deprecated APIs, data flow, navigation, and accessibility tailored to mistakes LLMs commonly make.
A 23-skill Claude Code toolkit that composes an LLM-driven virtual engineering team (CEO, designer, eng manager, QA, security, release) into slash-command workflows — includes real-browser QA, a persistent GBrain memory, multi-agent integrations, and team auto-update semantics.
Gives the pi terminal AI agent an autonomous experiment loop: propose code changes, run benchmarks, record metrics, auto-commit improvements and revert regressions. Ships a live widget/dashboard, MAD-based confidence scoring, hooks and backpressure checks — made for iterating on speed, bundle size, training loss and build times inside a terminal workflow.
Reverse-engineers live websites into production-ready Next.js codebases: an AI-driven /clone-website skill extracts design tokens, assets, and exact component specs, then dispatches parallel builder agents to reconstruct pages. Recommends Claude Code (Opus 4.7) but supports many agents.
Turns any codebase, docs, or wiki into an interactive knowledge graph for exploration, semantic search, and Q&A. Uses a Tree-sitter + multi-agent LLM pipeline to auto-generate node summaries, guided tours, and diff impact analysis; CLI and dashboard integrations.