AI Agent Tools

graphify105.4k★

Graphify reads your entire codebase, docs, PDFs, and even screenshots, then builds a knowledge graph you can actually navigate. It parses 19 languages via tree-sitter for code and uses an LLM for everything else. The result is an interactive HTML visualization showing how your architecture, concepts, and files connect. The first extraction pass costs real API tokens (Claude or GPT), proportional to your corpus size. After that, incremental updates via SHA256 caching mean re-runs only process changed files. The 71x token compression claim is real for subsequent queries, not the initial scan. Runs as a /graphify slash command inside Claude Code, Codex, or OpenCode. For developers onboarding to large or unfamiliar codebases: this is genuinely useful. Architecture reviews, cross-referencing code with design docs, understanding how a monorepo fits together. Exports to Neo4j, Obsidian vaults, or standalone wikis. The catch: it is a plugin, not a standalone tool. You need Claude Code or a compatible AI assistant as the runtime. Quality of inferred relationships depends on the underlying LLM, and the initial scan of a large repo is not cheap.

caveman98.0k★

Caveman strips the fluff from Claude Code responses. Install it with one command, activate with /caveman, and your AI assistant drops the pleasantries, hedging, and filler words while keeping full technical accuracy. Average savings: 65% fewer output tokens. Multiple intensity levels: Lite stays professional but terse, Full drops articles and uses fragments, Ultra goes telegraphic, and Wenyan variants compress into classical Chinese. Code blocks, error messages, git commits, and technical terms pass through untouched. Version 2 added a compression engine that squeezes model input as well: tool outputs, logs, and JSON get compacted before they hit your context window, and a companion tool rewrites your CLAUDE.md and memory files to cut input tokens too. It works across 30+ AI coding agents, not just Claude Code. Cursor, Copilot, Windsurf, Cline, Codex, all supported. Heavy token users will feel the difference in both speed and cost. The catch: it started as a meme but the benchmarks are real, backed by a real 2026 research paper. Ultra mode can be hard to read. And v2 split the licensing: the skill, CLI, and SDKs stay MIT, while the engine, proxy, and platform components moved to BSL-1.1, free to self-host including production, only blocking resale of Caveman as a service. The split is per-component, so the LICENSE file in each package is the authority.

OpenViking28.2k★

OpenViking is a context database built specifically for AI agents. Instead of the usual pile of vector embeddings, it organizes an agents memory, retrieved documents, and skills the way a filesystem organizes files: directories you can navigate, tag, and search recursively. It is open source under AGPL-3.0. Setup is heavier than a typical pip install. You will need Python 3.10+, a Rust toolchain for building the RAGFS component, and a C/C++ compiler for the core extensions, on top of wiring up a vision-language model and an embedding model (Volcengine Doubao, OpenAI, or others) before it does anything useful. Once running, it compresses conversation history automatically and shows you the retrieval path it took to answer a query, so debugging why an agent recalled the wrong thing is actually possible. There is a hosted demo, OpenViking Studio, if you want to try the retrieval and memory features before committing to the build. Solo devs experimenting with agent memory: worth the setup time if you are hitting the limits of flat vector search. Teams building production agents: the tiered loading, it only pulls in the context tier it actually needs, is the real selling point for cutting token costs at scale. It is AGPL-3.0, not MIT or Apache. If you build a hosted product on top of OpenViking and offer it as a network service, the license requires you to open source your modifications too. That is a real constraint for anyone planning to build a commercial product on this, not just an internal tool.

claude-obsidian10.8k★

claude-obsidian turns an Obsidian vault into something a coding agent can actually work in. Drop a source in and the agent reads it, pulls out entities and concepts, writes cross-referenced pages, and keeps the links honest. Your vault stays a plain directory of Markdown files rather than a proprietary database, which is what matters if you expect to still have these notes in five years. MIT licensed. Now at v2.1.0 with 15 skills spanning ingestion, querying, wiki building, linting, research, and Canvas generation. Operations are transactional with rollback and conflict detection, which sounds dull until an agent half-finishes a bulk edit across 200 notes. Needs Python 3.11 or newer plus bash. Obsidian itself is optional, since the output is just Markdown. It no longer assumes Claude Code. Cursor, Windsurf, Codex, OpenCode, and Gemini all work, and you choose a methodology up front: generic, LYT, PARA, or Zettelkasten. Solo note-takers and researchers get the most out of it. Small teams can share a vault through git. Medium and large teams should not expect a multi-user story, because there is not one. The catch is the agent bill. Every ingest and wiki-build pass burns a lot of tokens against whatever agent you point at it, and re-linting a large vault is not cheap. The sharper catch: an agent that writes your notes writes its mistakes into them confidently. Source traceability tells you where a sentence came from, not whether it is true.

get-shit-done-redux8.1k★

get-shit-done-redux is a system for keeping AI coding assistants reliable over long sessions. The problem it targets is context rot, the quality drop that happens as an agent fills its context window and starts forgetting what it was doing. GSD fixes this with a structured command loop and fresh subagent contexts, so the main window stays uncluttered. It works with Claude Code, OpenCode, Gemini CLI, and others. MIT licensed and free. The workflow is six commands: start a project, discuss the phase, plan it, execute through parallel agents, verify the result, then ship and repeat. Each executor gets its own clean context window, which keeps your primary session running at a fraction of capacity instead of choking on accumulated history. Install is a single npx command, so there is almost nothing to set up. Solo developers who run long agent sessions and watch quality degrade will get the most out of this. Small teams adopting a shared agent workflow can standardize on the same command loop. It is free at every scale, so the only cost is learning the discipline it imposes, which is the actual point. The catch is that this is methodology wrapped in tooling. It only helps if you commit to the loop. Bolt it onto a chaotic workflow and you will get chaos with extra steps. The structure is the value, and structure takes buy-in.

gsd-27.8k★

GSD-2 is a framework for keeping AI agents on track through long, complex tasks by giving them structured context and spec-driven goals. If you've used AI coding agents and watched them lose the plot halfway through a big refactor, this is the fix. The core idea is 'context engineering': you define specs that describe what the agent should build, break work into phases, and the framework ensures the agent always has the right information at the right time. Specs look like structured documents with acceptance criteria, constraints, and dependencies. Instead of the agent drowning in its own conversation history, GSD-2 feeds it focused context windows that keep each step scoped and grounded. The catch: growing fast, but the API is still evolving. Docs are catching up. This is a bet on a concept (structured agent orchestration) rather than a stable production tool. If you need something battle-tested today, look at established agent frameworks. If you want to experiment with the next wave of agent reliability, this is worth watching.

vibecode-pro-max-kit1.1k★

vibecode-pro-max-kit is an installable bundle of agents, skills, and lifecycle hooks for Claude Code, Cursor, Codex, and similar AI coding environments. The pitch is a spec-driven workflow that pushes you through research, innovate, plan, and execute phases with explicit approval gates instead of letting the agent run free. MIT-licensed, free, installed by curl. Setup is a 30-second curl that drops 12 specialized agents, 31 skills, and hooks into your project's .claude/ directory. The framework's bet is that disciplined phase gates beat raw agent autonomy: you don't get past planning without approving the plan, and you don't get past execution without a spec to check against. Works across any tech stack since it's harness-level, not language-level. For solo developers who keep losing context with vibe-coded agent runs, this is a structured replacement. Small teams adopting it together get a shared coding workflow without having to enforce one manually. Larger orgs will want to read what the agents actually do before standardizing on someone else's prompt library, but the core idea (gate the agent, don't free-run it) is good practice. The catch: this is an opinionated workflow, not a tool. Skip the gates and you've installed 12 agents producing noise. The upstream also changes whenever the maintainer changes their mind, which is its own kind of dependency. If you want to enforce spec-driven coding with AI, this is one way; if you want the agent to be fast and loose, skip it.

book-to-skill1.0k★

Feed it a technical book and it hands back a skill your coding agent can actually search. The pitch is token economy: instead of dumping 400 pages into context and paying for every one of them, the generated skill loads only the chapters relevant to the question. The project claims 24x to 51x fewer tokens per answer. MIT licensed, runs entirely on your machine, no API key. Setup is three commands: pip install, register the skill, point it at a file. Format support comes through optional dependencies, so PDFs want pdftotext or pypdf and EPUBs want ebooklib. Nothing gets uploaded. Output works with Claude Code, GitHub Copilot CLI, and Amp. The obvious use is reference material your agent keeps guessing about: language specs, framework books, internal standards documents. Solo and small teams: free, and no reason not to try it on one book first. Medium and large teams get more out of converting shared internal docs once and committing the result. The catch is legal, not technical. The MIT license covers the converter, not the book you put through it. Turning a purchased title into a skill you commit to a shared repo is redistribution, and the tool will happily let you do it. The other limit is mechanical: a scanned image-only PDF has no text to extract.

recall738★

Recall fixes the annoying part of working with Claude Code across sessions: re-explaining your project every time you come back. It captures what happened in a session, the prompts, the responses, the files you touched, the commands you ran, and boils it down to a short summary the agent can read next time to pick up where you left off. MIT licensed, free, and it runs entirely on your machine. The clever bit is that it summarizes locally with classic text-ranking algorithms, TF-IDF and TextRank, so there is no extra LLM call and no token cost for the summary itself. It drops two files in a .recall/ folder: an append-only history log and an auto-generated context digest with your goal, key files, and next steps. It even redacts common secret patterns before writing anything to disk. No setup, works offline. This is a Claude Code plugin, not an MCP server, so it slots into the workflow without extra infrastructure. Solo developers juggling several projects get the most out of it: a 1 to 2K token digest is far cheaper than pasting your whole project history back in, and it works with whatever Claude subscription you already have. The catch is that a TF-IDF summary is compression, not understanding. It surfaces what looks important by word frequency, which is usually enough to orient the agent but occasionally misses the one detail that mattered. Skim the context file before you trust it to have remembered everything.