Bookmarks

Agent Toolkit — Full Archive

Skills & Capability Packs

anthropics/skills

Anthropic's own skill collection is the reference implementation of the Agent Skills spec: document creation for docx, pdf, pptx, and xlsx, Playwright-based webapp testing, and a skill that writes new MCP servers for you. Add it with `/plugin marketplace add anthropics/skills`, then `/plugin install document-skills@anthropic-agent-skills` (swap in `example-skills` for the other set). With 171k stars and commits landing this week, it's the version everyone else's skill pack gets measured against. **Pricing:** free, open source.

obra/superpowers

Superpowers turns a set of coding habits into skills that fire automatically mid-session: brainstorming before building, TDD's red-green-refactor, systematic debugging, working in git worktrees. Install with `/plugin marketplace add obra/superpowers-marketplace` then `/plugin install superpowers@superpowers-marketplace`. Version 6.3.0 shipped August 12 with Devin CLI and Hermes Agent support, and at 276k stars it's become close to a shared methodology for this ecosystem. **Pricing:** free, open source.

Vincentwei1021/video-shotcraft

Five weeks old and already past 6,000 stars: video-shotcraft hands Claude Code or Codex a library of 152 cinematic shot recipes and 200 motion previews so it can cut a beat-synced promo video in Remotion instead of guessing at camera language. Clone the repo and symlink it into `~/.claude/skills/video-shotcraft`. Commits have landed almost daily since it launched on July 19, 2026. **Pricing:** free, open source.

Trail of Bits Skills

Trail of Bits turned its own audit playbook into a skill pack: static-analysis orchestration across CodeQL and Semgrep, smart-contract vulnerability scanning across six chains, constant-time analysis, and differential code review, built by a firm that gets paid to find what everyone else missed. `/plugin marketplace add trailofbits/skills` installs the set in Claude Code or Codex. Past 7,700 stars with a commit the same day as this digest, it's becoming the default when a security team wants its own review habits built into an agent instead of left to memory. **Pricing:** free, open source (CC-BY-SA-4.0).

Remotion Agent Skills

Eleven skills make up this pack for Remotion's React video library: compositions, map animations through Mapbox or CesiumJS, caption generation, Studio interactivity, and package upgrades. `npx skills add remotion-dev/skills` installs them directly, or just say yes when `bun create video` offers to add them for you. At 5,500 stars with a commit landing today, the pack tracks the library it documents closely enough to trust. **Pricing:** free, open source.

HashiCorp Agent Skills

HashiCorp writes its own style guide into code here: sixteen Terraform skills and four Packer skills that produce HCL the way HashiCorp's engineers would, generate `.tftest.hcl` test files, and scaffold new modules. `claude plugin marketplace add hashicorp/agent-skills` then `claude plugin install terraform@hashicorp` installs it. It's a vendor repo rather than a crowd favorite, which is exactly the point when you want the skill to match the maintainer's own conventions. **Pricing:** free, open source.

Unity Agent Plugin

Twenty-nine Unity Editor skills shipped in about six weeks: a `unity-cli` for driving the Editor from a terminal, plus workflows for new-project setup, URP rendering, UI Toolkit, 2D and sprites, audio, multiplayer, IAP, ads, and localization. Unity made this live on September 9, 2026, and it's still labeled beta at v0.1.8. `/plugin marketplace add Unity-Technologies/unity-agent-plugin` then `/plugin install unity@unity-agent-plugin` gets it running. **Pricing:** free, official Unity-supported plugin.

VoltAgent/awesome-agent-skills

Over 1,500 skills sit in this directory now, curated from real engineering teams at Anthropic, Microsoft, Google, and Vercel rather than mass-generated filler, so it's worth checking before you write your own from scratch. Each entry links out through officialskills.sh to that skill's actual install steps, which vary by author. **Pricing:** free, open source.

vercel-labs/agent-skills

`npx skills add vercel-labs/agent-skills` drops in Vercel's own pack: forty-plus React and Next.js performance rules, a hundred-plus accessibility checks pulled from their web-design guidelines, and a writing-guidelines skill that enforces their own prose standards. **Pricing:** free, open source.

posit-dev/skills

R and Python package developers get their own pack here: Shiny app theming, Quarto publishing, R package lifecycle management, and a `ggsql` skill for writing SQL through plain language, added September 14, 2026. `npx skills add posit-dev/skills --all` installs the full set, or `/plugin marketplace add posit-dev/skills` to pick categories individually. **Pricing:** free, open source.

Slash Commands & Prompt Packs

wshobson/agents

This plugin marketplace packages 105 slash commands with 202 agents and 181 skills, each written natively for its harness rather than as a lowest-common-denominator prompt, so the same install works across Claude Code, Cursor, Codex CLI, OpenCode, and Copilot. Run `/plugin marketplace add wshobson/agents` then `/plugin install <name>` for whichever set you need. It's pushed commits every day this week and sits at 39k stars, which makes it the default starting point for a command library. **Pricing:** free, open source.

hesreallyhim/awesome-claude-code

Check whether someone already wrote your slash command before you write your own: this is the list most Claude Code command recommendations trace back to, with a dedicated section linking straight to ready-to-drop `.md` files. Grab one and put it in `.claude/commands/`. At 52.9k stars and updated almost daily, it's the reference index rather than a random link dump. **Pricing:** free, open source.

ccplugins/awesome-claude-code-plugins

Most "awesome" lists just point elsewhere; this one hosts working plugins directly, among them `commit-commands`, `pr-review-toolkit`, `feature-dev`, and `security-guidance`, plus an index of third-party marketplaces. A backlog of pending submissions got cleared and merged on August 12, 2026, which is why the list is noticeably fuller than it was a month ago. Install with `claude plugin marketplace add ccplugins/awesome-claude-code-plugins`. **Pricing:** free, open source.

GitHub Spec Kit

Five slash commands, `/speckit.constitution`, `/speckit.specify`, `/speckit.plan`, `/speckit.tasks`, `/speckit.implement`, carry a feature from idea to shipped code, forcing an agent to draft a spec and a plan before it touches a single file. `uvx --from git+https://github.com/github/spec-kit.git specify init my-project` sets it up for whichever agent you name: Claude Code, Copilot, Cursor, or others. Past 142,000 stars with a commit today, it's the standard answer to "how do I stop an agent from guessing at requirements." **Pricing:** free, open source (MIT).

agentsys

A short set of commands, `/next-task`, `/audit-project`, `/gate-and-ship`, `/ship`, `/deslop`, `/perf`, sits on top of twenty-five plugins, fifty-five agents, and forty-seven skills, written to work the same way across Claude Code, OpenCode, Codex CLI, Cursor, and Kiro. Version 6.1.1 shipped October 6, 2026. `/plugin marketplace add agent-sh/agentsys` installs it, or skip the marketplace with `npm install -g agentsys && agentsys`. **Pricing:** free, open source (MIT).

Claude-BugHunter

Eighty-three skills and fifteen slash commands turn Claude into a bug-bounty workflow covering OAuth and JWT exploitation, SSRF and RCE chains, and cloud misconfiguration, built around 681 patterns pulled from real disclosed reports. `/plugin marketplace add elementalsouls/Claude-BugHunter` then `/plugin install claude-bughunter@elementalsouls` installs it, or clone the repo and run `scripts/install.sh`. Over 5,200 stars and a commit today for a pack this specific says something about how many people now point agents at their own attack surface. **Pricing:** free, open source.

anthropics/claude-plugins-official

Anthropic runs its own plugin directory now, split into an internal `/plugins` folder it maintains directly and an `/external_plugins` folder for vetted partner and community work, each one bundling commands, agents, skills, and MCP config together. `/plugin install <name>@claude-plugins-official` is the whole install. **Pricing:** free, open source.

davepoon/buildwithclaude

buildwithclaude.com indexes 175 commands and 117 agents directly, then points past its own catalog into more than 20,000 community plugins and 4,500 MCP servers it doesn't host itself, working more like a search engine for the rest of this list than a library of its own. `/plugin marketplace add davepoon/buildwithclaude` adds it, then install whatever turns up. **Pricing:** free, open source.

Wirasm/prp

PRP stands for Product Requirement Prompt, and the dozen commands here (`/prp-plan`, `/prp-implement`, `/prp-review`, `/prp-orchestrate`) carry a feature from spec through validation instead of leaving that structure up to you. A PR-triage command landed September 8, 2026 alongside a shorter repo name. Install with `/plugin marketplace add Wirasm/PRPs-agentic-eng` then `/plugin install prp-core@prp-marketplace`. **Pricing:** free, open source.

MCP Servers & Connectors

modelcontextprotocol/servers

The official MCP servers repo bundles filesystem access, git operations, web fetch, a memory knowledge graph, and sequential thinking, and most MCP clients ship it as their example config. Add a server with `npx -y @modelcontextprotocol/server-memory` for the TypeScript ones or `uvx mcp-server-git` for the Python ones. Closing in on 90k stars, it's still the place to start if you're not sure where MCP begins. **Pricing:** free, open source.

microsoft/playwright-mcp

Playwright-mcp gives an agent real browser control, clicking, filling forms, navigating, reading page state, through the accessibility tree instead of screenshots, so no vision model is required. The whole setup is one entry in `mcp.json` pointing at `npx @playwright/mcp@latest`. Microsoft maintains it directly, and at 36k stars it's the browser-automation server most people reach for first. **Pricing:** free, open source.

github/github-mcp-server

GitHub's own MCP connector for issues, PRs, code search, and reviews has been on close to a weekly release cadence: v1.7.0 in July moved it onto the new MCP spec's stateless sessions, v1.9.0 turned on semantic search by default, and v1.10.1 landed August 20, 2026. Point an `mcp.json` entry at the binary or Docker image from the README. It's already the default GitHub connector at 32.5k stars, but the release pace is the real reason to check in on it this month. **Pricing:** free, open source.

Sentry Toolkit

Sentry folded its MCP server into a broader toolkit this year alongside its CLI and shared packages, so error tracking, issue triage, and release data reach an agent through the same install as everything else Sentry ships. `claude plugin install sentry-mcp@sentry-mcp` wires it into Claude Code, or point `mcp.json` at `npx @sentry/mcp-server@latest --access-token=<token>` for stdio. Hand it an LLM key and its embedded-agent mode can investigate and summarize an error on its own. **Pricing:** open source server; requires a Sentry account (free tier available, paid tiers for scale).

Supabase MCP Server

One `mcp.json` entry pointed at `https://mcp.supabase.com/mcp` lets an agent query tables, run SQL, manage migrations, and read edge-function logs against whichever Supabase project you authorize over OAuth. It's the vendor-maintained server, past 2,900 stars with a commit today, and it's usually the first one named when someone asks how to connect an agent to a Postgres backend without hand-rolling a connector. **Pricing:** free to connect; usage billed through your existing Supabase plan.

xTiles MCP

xTiles registered a remote MCP server on October 21, 2026, authenticated over OAuth 2.1 with PKCE instead of an API key, that turns chat output into real xTiles projects, pages, notes, and assigned tasks, and can read your calendar or pull an existing project back into the conversation. `claude mcp add --transport http xtiles https://mcp.xtiles.app/mcp` is the entire setup; the OAuth handshake runs itself on first connect. **Pricing:** freemium — free workspace tier, paid plans for teams.

TaskBullet MCP Server

Most MCP servers connect an agent to software. This one connects it to a person: `place_call` dials a real business phone number with a goal and a list of questions, a TaskBullet staffer makes the call, and the agent gets structured answers back plus a transcript through `get_transcript`. It surfaced on the awesome-mcp-servers list on October 21, 2026. `npx -y @taskbullet/mcp-server` with a `TASKBULLET_API_KEY` env var installs it, or hit the hosted endpoint directly. **Pricing:** paid, usage-based — $2.50 for the first minute, $1 a minute after, no free tier.

ChromeDevTools/chrome-devtools-mcp

Google's Chrome team maintains this one directly: real browser control through Puppeteer, DevTools performance traces, network inspection, and console output an agent can read without a screenshot. One `mcp.json` entry pointing at `npx -y chrome-devtools-mcp@latest` is the entire setup, and a `--slim --headless` flag trims it for simple tasks. **Pricing:** free, open source.

cloudflare/mcp-server-cloudflare

Cloudflare rebuilt every server in this repo on a new stateless SDK factory this year, so each one answers through the same `/mcp` endpoint instead of holding session state in memory, and the old SSE URLs now return a 410 with migration instructions. Point an MCP client at a remote URL like `https://docs.mcp.cloudflare.com/mcp` for documentation or `https://bindings.mcp.cloudflare.com/mcp` for Workers bindings; nothing runs locally. **Pricing:** free, usage-based on the Cloudflare resources it touches.

agentgateway/agentgateway

Everything else in this bucket is a single server. Agentgateway is the layer that sits in front of all of them, a Rust proxy that adds OAuth, content filtering, and observability to MCP and A2A traffic without touching the servers themselves. Standalone and Kubernetes quickstarts are both documented at agentgateway.dev. **Pricing:** free, open source.

Plugins & IDE Extensions

Claude Code for VS Code

Anthropic's official VS Code extension puts Claude Code inside the editor: inline diff review, @-mentions tied to your current selection, autonomous file edits and terminal runs, and a checkpoint system to roll back what it did. Install it from the VS Code Marketplace like any other extension. It's at 23.8 million installs with a version bump on August 18, 2026, which says something about how fast this one still moves at that size. **Pricing:** free extension, requires a paid Claude plan or API account.

Claudian

Claudian drops Claude Code, Codex, Grok, Opencode, and Pi into an Obsidian vault as agents that can read, search, and edit vault files directly, turning the vault itself into the agent's working directory. Install it from Community Plugins by searching "Claudian." It shipped v2.2.4 days before this digest went out and has already crossed 1.8 million downloads, unusually fast growth for a plugin this specific. **Pricing:** free, open source, bring your own agent CLI or API key.

Junie by JetBrains

Junie is JetBrains's own agentic coding tool for the IntelliJ family, IntelliJ IDEA, PyCharm, WebStorm, and it left beta for general availability in June 2026 with IDE-native context and an allowlist for terminal, build, and MCP actions. Install it from the JetBrains Marketplace like any other plugin. Bundled into the AI Pro and Ultimate subscription tiers, it's JetBrains's answer to what Claude Code and Cursor already do inside VS Code. **Pricing:** freemium, bundled with JetBrains AI Pro ($10/mo) or Ultimate ($30/mo).

Ollama AI for Raycast

Twenty-four commands put a local or remote Ollama model behind Raycast: multi-turn chat, one-shot writing and analysis tasks, vision support, and, as of Raycast's new provider API, the ability to supply its models to Raycast's own built-in AI Chat. Install from the Raycast Store by searching "Ollama AI." Past 42,700 installs with an update on September 28, 2026, it's the usual pick for anyone running models locally instead of through a hosted API. **Pricing:** free, open source; no cost beyond the models you already run.

Sider

A sidebar on every page you visit can chat with GPT, Claude, Gemini, Grok, or DeepSeek, summarize what's on screen, or run several of those models against the same question at once and compare the answers side by side, a group-chat feature most competitors skip. Install it from the Chrome Web Store. Five million users and a 4.9 rating make it one of the most-installed AI sidebars running, with version 5.35.3 shipping October 21, 2026. **Pricing:** freemium — limited free daily queries, paid plans for more.

Nanobrowser

Nanobrowser puts a small team of agents inside a Chrome extension instead of a server you run separately, splitting a web task like scanning GitHub Trending or comparing Amazon listings across specialized roles, and it works with whatever LLM key you already hold: OpenAI, Anthropic, Gemini, or a local Ollama model. Install from the Chrome Web Store, or load the unpacked build from GitHub releases for the newest features. **Pricing:** free, open source, bring your own API key.

Agent Loops & Harnesses

Ruflo (formerly Claude-Flow)

Claude-Flow renamed itself Ruflo this year and kept doing what made it popular: hierarchical swarm orchestration for Claude Code, with consensus-based coordination and vector memory that lets agents recall what worked in past sessions. Run `npx ruflo@latest init wizard`, or register it directly as an MCP server. Nearly 70k stars and daily point releases through this week keep it the default pick once a single agent isn't enough. **Pricing:** free, open source; a hosted web UI is a separate paid add-on.

ralphex

Ralphex runs Claude Code or Codex through a five-phase review loop per task: a fresh session, a parallel first review by five agents, an optional external Codex pass, a focused second review, then finalize, so each task gets checked before it's called done instead of trusting one long-running session. Install with `go install github.com/umputun/ralphex/cmd/ralphex@latest` or `brew install umputun/apps/ralphex`. Version 1.6.0 shipped June 26, 2026 with Fable model support and a web dashboard, and commits are still landing this week. **Pricing:** free, open source.

gh-aw (GitHub Agentic Workflows)

GitHub's own agentic-workflows project lets you define automations in Markdown and YAML that compile into GitHub Actions, splitting a read-only sandboxed agent job from a separately scoped job that applies the writes it produced. It's been in public preview since June 11, 2026 and already has 5,000 stars. Install it with `gh extension install github/gh-aw`. **Pricing:** free, uses your own Actions minutes and model API costs.

OpenClaw

OpenClaw doesn't run one model; it runs a control plane. A local Gateway manages sessions, tools, and events, and an Agent Client Protocol lets it spawn and coordinate Claude, Codex, or local models as interchangeable providers behind a persistent skills system reachable over Signal, Telegram, or Discord. It's grown fast enough to earn a Wikipedia page and regulatory attention in China, past 390,000 stars under the third name it's settled on. `curl -fsSL https://openclaw.ai/install.sh | bash` installs the Gateway; version 2.0 shipped August 30, 2026, with a paid Enterprise tier following a month later. **Pricing:** open source core (MIT); Enterprise tier is paid.

Pi

Pi's 1.0 release on October 1, 2026, added "virtual models": one model plans, a second does the typing, inside the same tool-calling loop, and MCP calls now route through a sandboxed JS layer the project says cuts prompt tokens by around 40%. Nine point releases landed in October alone, most recently v1.4.0 on October 21. `curl -fsSL https://pi.dev/install.sh | sh` installs the CLI. **Pricing:** free, open source (MIT); bring your own model API key.

oh-my-claudecode

A five-stage pipeline, team-plan, team-prd, team-exec, team-verify, team-fix, wraps Claude Code and loops the verify-and-fix cycle until a stage actually passes, instead of calling the job done after one run through, and routes the simpler stages to cheaper models to keep the bill down. It shipped v5.7.9 the same day as this digest, with nineteen specialized subagent variants and past 40,000 stars. `npm i -g oh-my-claude-sisyphus@latest` installs it, or add it as a Claude Code plugin. **Pricing:** free, open source; requires an underlying Claude Code subscription.

Hermes Agent

Most loops in this bucket repeat a fixed plan; Hermes writes and refines its own skills as it works, then nudges itself to save what it learned so the next session doesn't start from zero. It launched February 25, 2026 and has since passed a quarter-million stars, the fastest growth of anything in this space this year. `curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash` installs it, and it'll connect to Telegram, Discord, Slack, WhatsApp, or Signal if you want it reachable outside a terminal. **Pricing:** free, open source; model API costs are separate.

OpenHands Agent Canvas

Agent Canvas is OpenHands' control-center product: a self-hosted dashboard for running several coding agents as an always-on team, wired into Slack, GitHub, and Linear so a task can start from a ticket instead of a terminal command. `npm install -g @openhands/agent-canvas` followed by `agent-canvas` launches the full local stack. **Pricing:** free, open source.

Omnigent

Omnigent doesn't run any agent itself. It sits above Claude Code, Codex, Cursor, OpenCode, Hermes, and Pi as a shared policy and sandboxing layer, syncing a session across devices in real time. Version 0.14.0 shipped September 15, 2026, though the project still labels itself alpha. Install with `curl -fsSL https://raw.githubusercontent.com/omnigent-ai/omnigent/main/scripts/install_oss.sh | sh`. **Pricing:** free, open source.

CLI Agents & Runners

Claude Squad

Claude Squad runs several terminal agents, Claude Code, Codex, Aider, Gemini, OpenCode, Amp, side by side, each in its own git worktree and tmux session, with a TUI for reviewing diffs across all of them at once. Install with the one-line curl script or `brew install claude-squad`. It's at 8.4k stars with a commit as recent as August 20, 2026, and it's usually the first name that comes up when parallel agent sessions get mentioned. **Pricing:** free, open source.

CLI Agent Orchestrator (CAO)

AWS Labs built this to coordinate Claude Code, Codex, and Kiro as specialist workers under a supervisor agent, each isolated in its own tmux session so one agent's context doesn't bleed into another's. Run `uv tool install git+https://github.com/awslabs/cli-agent-orchestrator.git@main --upgrade`, or grab it from PyPI. It's shipping fast: v2.4.1 landed August 4, 2026, with commits nearly every day since. **Pricing:** free, open source.

Parallel Code

Parallel Code, from the developer behind Super Productivity, is a desktop app that fires off Claude Code, Codex, and Gemini on the same task in separate git worktrees, then lets you diff the results side by side and merge or discard each one. Download the DMG, AppImage, or .deb from the releases page, or build it from source. It's under 1,000 stars, but daily commits through August 21, 2026 make it early rather than untested. **Pricing:** free, open source.

OpenCode

OpenCode ships two built-in agents in one CLI: a build agent with full write access and a plan agent restricted to read-only analysis, backed by 75-plus model providers and LSP integration so it reads a project the way an editor would. It moved from the `sst` GitHub org to `anomalyco` this year, but the install command hasn't changed: `curl -fsSL https://opencode.ai/install | bash`. **Pricing:** free, open source; model API costs are separate.

ccmanager

ccmanager skips tmux entirely and builds its own TUI for running Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline, OpenCode, and Kimi CLI side by side in separate git worktrees, with a live busy, waiting, or idle indicator per session so you know which one actually needs you. `npm install -g ccmanager`, or skip the install and run `npx ccmanager` directly. **Pricing:** free, open source.

Conductor

Conductor is a Mac app rather than a CLI wrapper: it fires Claude Code, Codex, and Cursor at the same task in separate git worktrees, then lets you diff and merge or discard each result, with a Linear ticket as an optional starting point. Its changelog logged a version bump the same day this digest was written. Download it from conductor.build. **Pricing:** free.

Rules, Hooks & Guardrails

AGENTS.md standard

AGENTS.md is the format itself: one file in your repo root that over 30 coding agents, Claude Code, Cursor, Codex, Copilot among them, already read for project rules and context, so writing it once covers whichever agent a teammate happens to be running. There's nothing to install beyond the file. With nearly 24k stars and adoption across more than 60,000 repos, it's the closest thing this space has to a shared convention. **Pricing:** free, open standard.

cc-safety-net

cc-safety-net is a PreToolUse hook that catches destructive commands, `rm -rf`, force pushes, `dd`, `mkfs`, and reads of secrets like SSH keys or `.env` files before they execute, including ones buried inside shell wrappers or one-liners. Run `npx -y cc-safety-net@latest install` and it's wired in. The v2 line added support for a dozen agents beyond Claude Code and is shipping near-daily point releases, most recently August 23, 2026. **Pricing:** free, open source.

claude-code-hooks

This is a marketplace of about twenty installable hook plugins, blocking dangerous commands, protecting secrets, enforcing git safety, tracking context cost, each running as an out-of-process guard so a prompt injection inside the conversation can't disable it. Install the marketplace with `/plugin marketplace add karanb192/claude-code-hooks`, then `/plugin install <hook-name>@claude-code-hooks`. It's a smaller project, under 500 stars, but commits landed the same week as this digest. **Pricing:** free, open source.

Guardrails AI

Guardrails AI wraps a validator function around an LLM call to catch what shouldn't reach a user or a downstream system: PII, jailbreak attempts, toxic language, hallucinated claims, pulled from a hub of pre-built validators instead of a regex you write yourself. `pip install guardrails-ai` installs the framework; validators come from the Hub separately. **Pricing:** free, open source; hosted inference was retired August 25, 2026, so it now runs fully self-hosted.

Microsoft Agent Governance Toolkit

Microsoft built this to make a policy violation structurally impossible rather than trust a model to refuse on its own: it intercepts a tool call before execution and checks it against policy, with claimed coverage of all ten OWASP Agentic AI Top 10 risks plus NIST and EU AI Act mappings. `pip install "agent-governance-toolkit[full]"` covers Python; TypeScript, .NET, Go, and Rust packages ship separately. **Pricing:** free, open source.

Nono

Nono comes from the team behind Sigstore and skips containers entirely, using Linux Landlock or macOS Seatbelt to strip an agent's process privileges for the run, then sandboxing each tool it calls, git, curl, kubectl, in its own separate child sandbox so a compromised agent can't inherit more access than its policy allows. Trade coverage picked it up as an open-source AI agent sandbox on July 27, 2026. Install with `curl -fsSL https://nono.sh/install.sh | sh`. **Pricing:** free, open source.

Memory & Context

MCP Memory Service

MCP Memory Service gives an agent persistent memory across sessions, backed by local ONNX embeddings and a knowledge graph, with a REST API that also plugs into LangGraph, CrewAI, and AutoGen pipelines outside of Claude entirely. Run `pip install mcp-memory-service`, then point your MCP config at it. It's been running since December 2024, and v11.8.2 shipped the same day this digest was written, so it's actively maintained rather than coasting. **Pricing:** free, open source; optional paid Cloudflare sync.

Context Mode

Context Mode sandboxes noisy tool output before it reaches the model's context window, the project claims a 98% size reduction, and persists session state in SQLite so a compaction event doesn't erase what the agent already knew. It works across 17 coding-agent platforms through hooks; `npm install -g context-mode` plus one config line is the whole install. It crossed 20k stars fast after launching in February 2026, and the core stays free while a hosted cost-analytics dashboard is the paid layer. **Pricing:** free core, optional paid "Insight" cloud dashboard.

mcp-memory

Ten days old at the time of writing and already at 193 stars: mcp-memory stores an agent's memories as plain Markdown files in an OKF-like format, then indexes them in SQLite FTS5 for search that returns in under 20 milliseconds. Clone the repo, run `python3 setup.py`, then register it as an MCP server. It's a smaller, more legible alternative to memory servers that hide everything behind a database file you can't read. **Pricing:** free, open source.

Graphiti

Every entity and relationship in this knowledge graph carries a validity window instead of a single snapshot, so an agent can ask what was true at a given point in time, not just what's true now, and retrieval blends semantic embeddings, keyword search, and graph traversal without an extra LLM call at query time. `pip install graphiti-core` gets the library; Neo4j or FalkorDB runs behind it. Past 32,000 stars with a commit this week, it's the usual answer when agent memory needs to actually track change over time. **Pricing:** free, open source (Apache 2.0); backing store and LLM costs are separate.

Hy-Memory 2.0

Tencent's Hunyuan team rebuilt its memory library around three separate cognitive modes, chat, working, and coding, each with its own storage shape: eight-layer memory for conversation, a two-layer store for working context, and a diff-chain that versions what an agent has learned about a codebase over time. Version 2.0 shipped October 16, 2026. `pip install hy-memory==2.0.4` installs it against Chroma, Qdrant, or FAISS, with Neo4j or Kuzu available for graph mode. **Pricing:** free, open source (Apache 2.0).

agentmemory

Hooks into twelve coding agents, Claude Code, Copilot CLI, and Cursor among them, sort what gets captured into four tiers, working, episodic, semantic, procedural, store it in a SQLite file you can actually open, and retrieve it through a hybrid of BM25, vector search, and reciprocal rank fusion. `npx -y @agentmemory/agentmemory@latest` installs it, or run it as an MCP server with `npx -y @agentmemory/mcp`. Trending since May and still shipping, with a commit yesterday and nearly 30,000 stars. **Pricing:** free, open source; self-hosted, with roughly $10 a year in typical embedding costs.

Cognee

Documents, code, and conversation history go in; a self-hosted knowledge graph comes out, built through entity extraction and relationship mapping with vector search layered on top, and tuned to run against small local models so nothing has to leave your machine. `pip install cognee` gets the library; a `cognee-cli` adds `remember` and `recall` commands directly. At 32,700 stars and version 1.6.1, it's one of the more complete local-first options in this category. **Pricing:** free, open source (Apache 2.0); fully local-capable.

Mem0

Mem0 keeps memory at three levels, user, session, and agent, and retrieves by similarity instead of replaying a full transcript, which is why it's become the default answer whenever a tutorial needs "an agent that remembers." `pip install mem0ai` or `npm install mem0ai` gets the library; a hosted version and CLI exist too. **Pricing:** free, open source; managed hosting is a paid tier.

claude-mem

claude-mem watches every tool call in a Claude Code session, compresses what happened with a smaller model, and quietly reloads the relevant parts the next time you start working, so a session doesn't begin from nothing. It grew past 94,000 stars by the middle of this year and now reaches past Claude Code into OpenCode, Grok Bot, and Antigravity. `npx claude-mem install` sets it up, with an `--ide` flag for the others. **Pricing:** free, open source.

GoodMemory

GoodMemory is the small, legible option next to Mem0: memories live in plain SQLite, every one can be inspected, corrected, or deleted through a `forget` call, and nothing writes back to storage unless you opt in. It shipped its first stable release July 6, 2026 and reached v0.8.0 on September 14 with MCP tool exposure added. `npm install -g goodmemory@0.8.0` then `goodmemory setup` wires it into Codex or Claude Code. **Pricing:** free, open source.

Workflow Recipes & Templates

claude-code-templates

claude-code-templates is a browsable, installable library of ready-made agents, slash commands, hooks, and MCP configs. Running `npx claude-code-templates@latest` opens an interactive picker so you install exactly the bundle you need instead of copying files by hand. At 30.4k stars and commits landing today, it's usually the fastest way from an empty `.claude/` folder to a working setup. **Pricing:** free, open source.

maestro-flow

Maestro-flow's predecessor, the older Claude-Code-Workflow repo, was archived in June with a migration notice pointing here; the new version adds a knowledge graph so the planning, execution, and validation agents it wires together learn from past runs instead of starting cold each time. Run `npm install -g maestro-flow` then `maestro install` to get it working across Claude Code, Codex, and Gemini. Version 0.5.80, adding Arch-KB search templates, shipped the same day as this digest. **Pricing:** free, open source. --- *27 tools this week. Found a dead link or have something to add? Reply to the email.*

BMAD-METHOD

Seven persona agents, Analyst, PM, Architect, UX Designer, Scrum Master, Dev, QA, chain together so the planning agents write the PRD and architecture docs, the Scrum Master turns those into fully-contexted story files, and Dev and QA implement and gate the work before anything ships. `npx bmad-method install` sets up the stable v6.12 line; a v7 preview already sits on main. At 54,000 stars, it remains the reference for an agent team that mirrors a real software process instead of one long prompt. **Pricing:** free, open source (MIT), donations welcome.

pro-workflow

Eight role agents, planner, reviewer, scout, orchestrator, debugger, context-engineer, permission-analyst, cost-analyst, work alongside forty-one skills and thirty-three hook scripts spread across twenty-two lifecycle events, backed by a SQLite memory store that corrects itself over time and native git-worktree support for running sessions in parallel. Version 3.4.0 shipped September 28, 2026, adding an offline-trainable classifier layer. `/plugin marketplace add rohitg00/pro-workflow` then `/plugin install pro-workflow@pro-workflow` installs it in Claude Code. **Pricing:** free, open source.

coco

386 slash commands sit on top of Claude Code, Cursor, and Codex here, forty-six hand-written and the rest generated on demand, alongside 229 skills and a "routed advisory board" of expert personas you can call into an architecture decision instead of making it alone. `npx cocosuperintelligence` runs the installer, or clone the repo and run `install.sh`. It shipped v1.9.0 the same day as this digest. **Pricing:** open-core — MIT core, with a paid "Super Intelligence" layer for advanced features. --- *28 tools this week. Found a dead link or have something to add? Reply to the email.*

Evals & Agent Observability

Arize Phoenix

Phoenix captures LLM and agent runtime spans over OpenTelemetry, scores them against a dataset through a built-in eval module, and surfaces the whole thing in a self-hosted trace viewer you can actually debug a multi-step run in, rather than just read a log about. `pip install arize-phoenix` gets it running locally, with Docker, Railway, or cloud templates for anything bigger. The project patched a compromised litellm dependency in its October 22, 2026 release, the kind of maintenance worth checking for in anything sitting in your eval pipeline. **Pricing:** open source core; paid managed cloud tier available.

DeepEval

A pytest-native test runner scores LLM and agent output with research-backed metrics, G-Eval, task completion, tool correctness, computed locally, so a regression in agent behavior shows up the same way a broken unit test would in CI. `pip install -U deepeval` is the whole install, and it reads straight off LangChain or OpenAI agent traces. Version 4.3.1 shipped October 16, 2026, and past 19,000 stars, it's become the default when a team wants evals living in the same test suite as everything else. **Pricing:** open source, free to run locally; paid cloud dashboard for hosted monitoring.

Beagle

Beagle doesn't evaluate your agent; it evaluates your harness. A seed, baseline, propose, score, gate, land pipeline runs an "evolver" agent that proposes changes to how your agent is built, scores each proposal against benchmark suites like terminal-bench and swe-bench-verified using those benchmarks' own graders, and gates out anything that regresses before it lands. Salesforce AI Research's DarwinX algorithm, built on this pipeline, ranked first on the OSWorld 2.0 leaderboard in results published October 15, 2026. `git clone` plus `bash scripts/install.sh` sets it up; Python 3.12 and Docker are required. **Pricing:** free, open source (Apache 2.0).

Langfuse

Langfuse covers the whole loop an eval setup needs: tracing every LLM call, versioning prompts, running LLM-as-judge or custom evaluators against a dataset, and a playground for iterating without redeploying anything. `git clone` plus `docker compose up` gets a self-hosted instance running locally, with Kubernetes and cloud templates for production. **Pricing:** free, open source core; managed cloud and enterprise features are paid.

Opik

Opik chases the same job as Langfuse but leans harder into agent-specific tracing, following multi-step tool calls through sixty-plus framework integrations, and it stayed fully self-hostable under Apache 2.0 even after a 2026 Gartner report named it in its market guide for AI evaluation platforms. `pip install opik && opik configure` gets the SDK; `./opik.sh` after cloning runs the full self-hosted stack. **Pricing:** free, open source; Comet's managed cloud is a paid tier.

hwatu

Everything upstream in this bucket traces LLM calls; hwatu checks whether the resulting UI actually rendered right. A WebKitGTK daemon opens a window in about 13 milliseconds, screenshots it, and scores the pixel difference against a baseline so an agent can iterate on a fix instead of guessing, with a handoff to a human mid-session when it hits a CAPTCHA. It surfaced on Hacker News around July 29, 2026. Install with `curl -fsSL https://raw.githubusercontent.com/hongnoul/hwatu/main/scripts/install.sh | bash`. **Pricing:** free, open source. --- *27 tools this week. Found a dead link or have something to add? Reply to the email.*