Earthworks

The coding-agent CLI my agents run inside: a terminal harness that gives a model file, shell, and subagent tools under operator control, with durable sessions and worktree isolation. Every agent session described on this site happens in it.

by Mario Zechner / earendil-works

• Running coding agents in a terminal with durable sessions and operator-held gates
• A harness built to extend: the other pi entries in this catalog are extensions of it

source & install at pi.dev

Extension for the pi coding agent that adds bounded subagent delegation: parallel reviews, scripted multi-child workflows, async work, and worktree isolation.

by Nico Bailon

• Teams on the pi harness that need safe parallel agent fan-out
• Code review and research sweeps without context contamination

install via npm · source

pi extension that keeps raw command output out of the model's context window. Code runs over big logs and files in a sandbox; only the derived answers enter the conversation.

by Mert Köseoğlu

• Agents drowning in build logs, API responses, or large file reads
• Long sessions where context rot degrades judgment

install via npm · source

Web access for pi agents: multi-provider web search, URL fetching, GitHub repo cloning, PDF extraction, and YouTube and local video understanding, all behind one tool surface.

by Nico Bailon

• Agent research sessions that need search and page reads without leaving the harness
• Video, PDF, and repository intake inside a coding session

install via npm · source

Lets pi drive your existing signed-in Chrome profile after explicit authorization, so agent browsing works with the sessions you already have.

by tianrendong

• Agent browsing against sites you are signed into, with the consent gate explicit
• Testing flows that depend on an authenticated browser profile

install via npm · source

A web dashboard for browsing, installing, and removing pi packages, plus a /packages command inside the TUI.

by JVKE

• Keeping the pi extension set visible and manageable from one surface

install via npm · source

Retries the provider errors that lose a turn for nothing: empty-detail responses, Codex websocket limits, and stalled requests.

by narumiruna

• Long unattended runs where a transient provider error should not end the job

install via npm · source

Fuzzy file and content search for pi, powered by the FFF engine: fast find across a repo from inside the session.

by Dmitriy Kovalenko

• Large-repo navigation without shell gymnastics

install via npm · source

Compacts context with the outgoing model before a switch to a smaller-window model, so the new model starts from a summary it can fit.

by Eran Sandler

• Moving a session down from a large-context model without losing the thread

install via npm · source

Checkpoint compaction for pi: structured engineering handoff summaries with model-selected cut points and full artifact tracking.

by taylorsatula

• Long builds where a plain summary loses the engineering state

install via npm · source

Read-only prepare mode for pi: clarifying questions, a structured plan for approval, tracked execution, and a clean-workspace dossier before implementation.

by taylorsatula

• Front-loading questions and plan review before any file changes

install via npm · source

A todo list for the model, rendered as a live overlay in the TUI that survives /reload and conversation compaction.

by juicesharp

• Keeping multi-step agent work on rails across a long session

install via npm · source

A second opinion the model can request from a stronger reviewer model before it acts.

by juicesharp

• Cheap insurance on consequential edits: a stronger model reviews before the change goes in

install via npm · source

The LunaRoute extension for pi: login, model sync, request attribution, and first-class web tools wired to my default gateway.

by LunaRoute

• Keeping the gateway model catalog in sync with the harness
• Attributing agent requests to the right workspace

install via npm · source

The pi integration herdr installs and manages: it reports live agent-session state to the herdr server over the pane socket, which is what lets panes auto-resume with their sessions.

by herdrdev

• Agent fleets in herdr panes that survive restarts with session state intact

source & install at herdr.dev

Memory layer for pi that injects persona and owner facts into agent sessions, so an agent arrives already speaking in the operator's voice and knowing the working context. Built on the paia memory system and delivered privately with engagements.

by Braydon

• Agent sessions that need persona continuity and owner facts from the first message
• Standing up the same memory-backed agent practice inside a client environment

installed with your engagement

Builds pi-memory's local classify request to Ollama under a pinned contract: strict JSON, thinking off, and a capped context so the call finishes in seconds. Pure module with its own tests.

by Braydon

• The judgment step of pi-memory's automatic memory loop

installed with your engagement

Namespace guards for pi-memory's facet keys: the fixed list of valid namespaces plus a normalizer that strips the subject prefix the local classifier invents. Pure string logic with its own tests.

by Braydon

• Keeping memory facets queryable instead of silently mistagged

installed with your engagement

Triage for pi-memory's staged record writes: separates clean, idempotent, warn, and failed outcomes, keeps the real traceback, and logs to a file instead of the TUI. Pure module with its own tests.

by Braydon

• Idempotent record staging that never interrupts a session with a false error

installed with your engagement

Guards every bash tool call in a pi session: rewrites whole-command grep to ripgrep, injects tiered fallback timeouts when the agent sets none, and blocks recursive searches rooted at the workspace container.

by Braydon

• Agent sessions that stop hanging on pathological shell commands

installed with your engagement

Probes running llama-server lanes over HTTP and registers the live ones as pi models under the local/ provider namespace, with /llama status, refresh, start, and stop commands.

by Braydon

• Local llama.cpp lanes as selectable models inside the harness

installed with your engagement

Sanitizes the tool schemas in pi's outgoing provider requests so Ollama-served models accept them. The installed build is a diagnostic pass that logs each request to disk.

by Braydon

• Mixing local Ollama models into pi without schema rejections

installed with your engagement

Switches the pi TUI between desktop and mobile chrome by terminal width or manual command, owns the footer widget slots, and clears the powerline status line on every view change so chrome never double-renders.

by Braydon

• One pi console across desktop panes and phone screens

installed with your engagement

A live-updating sidebar for the pi TUI with five tabs: session context and model history, an on-demand summary, the todo list, git state, and pane info.

by Braydon

• A glance view of the session without leaving the editor pane
• Watching context, todos, and git while the agent works

installed with your engagement

A side panel for the pi TUI that renders markdown as formatted terminal output, so you review what the agent wrote without leaving the terminal. /md opens the most recent markdown the session touched; a gitignore-aware browser picks any other.

by Braydon

• Reviewing agent-written docs in place
• Reading long markdown without a context switch

installed with your engagement

My tmux pane switcher for the pi TUI: a preview-first picker with flip navigation, pane links, visible spawning, and a global tmux manager agent.

by Braydon

• Driving a tmux agent fleet from inside one pi session

installed with your engagement

My herdr pane switcher for the pi TUI: a preview-first picker with flip navigation, pane links, visible spawning, and a global herdr manager agent.

by Braydon

• Driving a herdr agent fleet from inside one pi session

installed with your engagement

Bare completion mode for slow local base models: strips the pi request to just the latest message, with tools and history removed, so a slow prompt pass finishes before the watchdog aborts.

by Braydon

• Wringing answers out of big local models on modest hardware

installed with your engagement

Runs one approved shell command with administrator privileges after explicit consent: sudo authentication, a deletion-classification gate, and no password in the agent's hands.

by Braydon

• Global or destructive operations that need root without handing over a shell

installed with your engagement

The Workgraph bridge for pi: exposes the wg task verbs (claim, log, done, fail) as agent tools and adds a graph widget so the task board is visible inside the session.

by graphwork

• Agents that work the task graph under the same gates I use

source & install at github.com/graphwork/wg

Orca-managed integration installed by the Orca app: posts agent status snapshots (session, model, and tool events) to Orca's local hook receiver so the ops view stays current.

by Orca

• Agent status inside the Orca ops surface

installed with your engagement

Orca-managed integration: when Orca hands the pane a prefilled prompt, this drops that text into the pi editor at session start.

by Orca

• Composing a prompt in Orca and sending it to the pane clean

installed with your engagement

Orca-managed integration: animates a braille spinner into the terminal title while the agent works and restores the session title when it stops.

by Orca

• Telling busy panes from idle ones at a glance

installed with your engagement

The work-coordination graph every agent task on this site runs through: tasks with dependencies, dispatcher-spawned workers in isolated worktrees, receipt-backed completion, and evidence fencing for humans and AI agents. This catalog was built by agents dispatched through it.

by graphwork

• Coordinating multiple coding agents on one graph without stepping on each other
• Task work with deterministic completion checks and fenced evidence

source & install at github.com/graphwork/wg

A pane-based agent multiplexer: a persistent headless server owning real PTYs, with TUI clients, workspaces, tabs and panes, and live agent-session state for auto-resume.

by herdrdev

• Operating a fleet of coding agents in panes with sessions that survive a restart
• Replacing ad-hoc tmux sprawl for agent ops

source & install at herdr.dev

Headless browser engine written in Rust for scraping and agent automation. Real V8 JavaScript, Chrome DevTools Protocol, a drop-in for headless-Chrome workflows, and it ships an MCP server.

by h4ckf0r0day

• Agent web automation without a Chromium install
• MCP-driven browsing from any coding agent

source & install at github.com/h4ckf0r0day/obscura

Open-source team chat with threads; I run it as the message channel between agents and people across engagements.

by Zulip

• Threaded async coordination for distributed teams and agent fleets
• Self-hosted messaging where data stays in-house

source & install at github.com/zulip/zulip

The terminal multiplexer: persistent sessions, panes, and windows that survive disconnects. It is the substrate I run multi-agent fleets on.

by tmux

• Multi-agent orchestration: one pane per coding agent, with sessions that outlive the connection
• Durable remote sessions on headless hosts, resumable later from desktop or mobile

source & install at github.com/tmux/tmux

Z.ai's GLM-5.2, my standard work plane. Task-graph workers and dispatched agent runs execute on it at high reasoning by default; the gateway adds a vision serving of the same model, catalogued on its own row.

by Z.ai

• Default execution model for agent task graphs
• Long coding sessions that need steady high-reasoning output

source & install at z.ai

Z.ai's GLM-5-turbo, configured as the task-graph fast tier for high-volume generation where throughput beats depth.

by Z.ai

• Bulk drafts and research sweeps at low cost
• Fast turnaround steps inside multi-model workflows

source & install at z.ai

Moonshot AI's Kimi K3, routed direct from Moonshot's API; the coding-strong alternate in my model rotation.

by Moonshot AI

• Coding-heavy sessions as a second engine
• Long-context reading and editing

source & install at www.moonshot.ai

Open-source (Apache 2.0) System-1 judgment model that turns natural language and application state into typed judgments with calibrated probabilities. I run it locally on my GPU as the open counterpart to the commercial judgment APIs.

by NandhaKishorM

• Fast local classification, gating, and triage decisions
• Judgment steps that must run without an API call

source & install at huggingface.co/convaiinnovations/laya

TypeSafe's flagship System One model: typed answers with calibrated probabilities over a commercial API, instead of generated text. The commercial counterpart to open-weights Laya, and the model kev-4b is benchmarked against.

by TypeSafe

• Programmable common sense: routing, ranking, extraction, and verification steps in product code
• Judgment calls that need an API and a service level, not a local GPU

source & install at typesafe.ai

Qwopus3.6-27B-v2-MTP, Jack Rong's multi-token-prediction fine-tune of Qwen3.6-27B, pulled as the Q4_K_M GGUF from Hugging Face via Ollama and served locally in my llama-lanes stack. Origin verified from the on-disk Ollama manifest; it is a downloaded community build, not one of mine.

by Jack Rong

• Local experimentation in the interactive plane

source & install at huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

API home of the GLM model family. My standard plane runs here: GLM-5.2 at high reasoning as the task-graph default, with GLM-5-turbo as the configured fast tier.

by Z.ai

• The default model plane for dispatched agent work
• High-reasoning coding and writing models at subscription rates

source & install at z.ai

My default model gateway: one subscription account serving the whole hosted roster, from GLM base, vision, and flash variants to DeepSeek, kev-4b, and the image models, with background serving modes for long jobs and an account-wide catalog that syncs into the agent harness.

by LunaRoute

• One subscription surface for text, vision, and image models
• Background serving variants for unattended generation jobs

source & install at lunaroute.com

Direct API route for the Kimi model family; Kimi K3 is in my interactive rotation for coding-heavy sessions.

by Moonshot AI

• Coding-strong alternate models when the primary plane is busy
• Long-context reading and editing in the Kimi family

source & install at www.moonshot.ai

Local open-weight model runtime. I keep a local lane on it for private, offline inference alongside the hosted planes.

by Ollama

• Private inference where data stays on the machine
• Offline and air-gapped agent work

source & install at ollama.com

A software-development methodology for coding agents, delivered as a fourteen-skill set (brainstorming, test-first development, systematic debugging, planning, code review) that make the agent work to a discipline instead of improvising. The full set installs from the upstream repo.

by obra

• Any team whose AI coding agent produces clever but undisciplined work
• Standardizing design-before-code, test-first, and verification habits across engineers

source & install at github.com/obra/superpowers

Workgraph-first autopilot for coding agents: dependency-aware execution graphs with drift checks (code, spec, scope) that keep implementation, spec, and intent synced without hard blocks. Two installed skills: the speedrift driver and rifts, a compatibility alias that routes to the same workflow.

by Braydon

• Multi-task agent projects where the work falls out of sync with the spec
• Turning a design spec into a verifiable execution graph

source & install at github.com/dbmcco/speedrift-ecosystem

Methodology and skill files for designing expert ensembles: domain-expert personas coordinated through a fixed inherited method, for standing analysis panels or one-shot live casts.

by Braydon

• Building a repeatable analyst panel for a domain you work repeatedly
• Casting a small expert ensemble for an immediate decision

installed with your engagement

Planning and Workgraph compilation pipeline: discovery, decomposition, a critic pass, and module selection that turn a goal into an executable graph with tests and drift gates.

by Braydon

• Front-end planning for agent execution graphs before code starts
• Turning strategy work into scheduled, verifiable tasks

installed with your engagement

Drafting, sequencing, personalizing, staging, and QA discipline for outbound email, LinkedIn, investor, and BD outreach; process craft for outreach that reads human.

by Braydon

• Founders and BD leads running multi-touch outbound with an agent
• QA gates that stop embarrassing sends

installed with your engagement

Research, qualification, segmentation, and prioritization method for prospect, partner, investor, and candidate lists; the upstream half of the outreach pipeline.

by Braydon

• Building ranked target lists with evidence instead of vibes
• Pre-outreach research sweeps an agent can run repeatedly

installed with your engagement

Craft system for writing and speaking in a named voice: voice packets distilled from edited drafts, with a learning loop that turns user corrections into reusable tone guides.

by Braydon

• Executives who need an agent that writes in their actual voice
• Building a house voice a whole team can execute

installed with your engagement

Design discipline for systems where an AI model owns the judgment calls (routing, ranking, extraction, verification) instead of hiding decisions in regexes, thresholds, and fallback code.

by Braydon

• Teams shipping AI features that keep accumulating hard-coded heuristics
• Architecture reviews of model-facing APIs and agent workflows

installed with your engagement

Thirty-five skills that drive the Google Workspace CLI across every Workspace surface: Drive, Docs, Sheets, Slides, Calendar, Chat, People, Tasks, Meet, Forms, Keep, Admin reports, Model Armor, cross-service workflow recipes, and the profile router that picks the right account before any call. The set builds on the open-source Google Workspace CLI, whose repo ships the tool and its agent skills.

by Google

• Agent workflows over a company's Google Workspace: documents, sheets, calendar, and chat from one CLI
• Reference architecture when an engagement needs Workspace-side automation design

source & install at github.com/googleworkspace/cli

Four wrapper skills that query an archived mail and message store from agent sessions: archive operations, message search, SQL analytics over volume, and attachment export. Three install from msgvault, the open-source archive service whose repo ships the service and its query skills; the fourth is a local operations reference for the archive it searches.

by kenn-io

built on msgvault by kenn-io; three of the four ship from its skills installer, and the archive-ops wrapper is mine

• Executive message history an agent can search without cloud APIs
• Email-derived intelligence with the archive staying on-prem

source & install at github.com/kenn-io/msgvault

Eight review-workflow skills for the roborev review daemon: requesting commit and branch reviews, working the iterative fix loop, responding without code changes, addressing specific jobs, and closing findings. Wired to per-repo review configuration; the daemon is local tooling with no verified public distribution, so the set installs with an engagement.

by Braydon

• Code review loops an agent runs on its own branches
• Design review on material diffs before they merge

installed with your engagement

Routes each turn of work to the right model tier before it starts: judgment and final calls stay on the strong model, volume generation drops to the fast tier, and anything that touches private data runs on local models only. Encoded as a disposition an agent applies to every task.

by Braydon

• Keeping strong-model spend on judgment instead of bulk generation
• Private data work routed to local-only models by default

installed with your engagement

Four runbook skills that recover and orchestrate an agent fleet: post-reboot workspace recovery, discovering and steering coding agents across terminal panes, and two coordinator playbooks for multi-agent work with mandatory verification. Authored against real hosts, so they install with an engagement and get rewritten for yours.

by Braydon

• Recovering an agent workspace after a reboot or OS update
• Orchestrating multiple coding agents in terminal panes with verification gates

installed with your engagement

Skill wrapper that drives the Folio CLI for notes, daily notes, collections, and search from agent sessions. The Folio applet entry describes the knowledge store behind it; the wrapper installs alongside a Folio setup.

by Braydon

• Note operations and knowledge lookup from any agent session
• Daily-note and collection workflows against a Folio store

installed with your engagement

Drives Supernote Cloud notebooks from agent sessions: list and read pages, append, move, and plan notes, with auth handled by the bundled CLI. Open source; the repo builds both the CLI and the skill that runs it.

by Braydon

• Filing and reading handwritten notes from an agent session
• Turning a Supernote into a queryable part of the workflow

source & install at github.com/dbmcco/paia-supernote

Legacy vault access, migration, and debugging for Obsidian-based stores. Useful when an engagement starts on an Obsidian vault and consolidates onto a queryable knowledge store.

by Braydon

• Migrating an existing Obsidian vault without losing structure
• Debugging vault plugins and link rot during a consolidation

installed with your engagement

Analyzes archived coding-agent transcripts with go-minitrace: find sessions by repository and date, attribute implementation work to a session, query normalized transcript tables, and report evidence with explicit caveats. Reads local transcript stores, so it deploys per engagement.

by Braydon

• Attributing implementation work to past agent sessions
• Comparing agent behavior across tools with cited evidence

installed with your engagement

Two wrapper skills for the workboard and program surfaces: task-board operations (claiming, status, comments, handoff) and research-backed program management with approval gates and execution ledgers. The Workboard and program applet entries describe the services; the wrappers install with them.

by Braydon

• Working a task graph from any agent session
• Program management with model-authored records and review gates

installed with your engagement

Third-party skill for building with TypeSafe System One models: typed judgments with calibrated probabilities used like programming primitives for routing, ranking, extraction, and verification steps in product code. MIT-licensed skill file; the platform and docs are the upstream.

by TypeSafe

• Designing AI features where judgment calls become typed decisions
• Cookbook patterns for routing, ranking, and verification with Jev

source & install at typesafe.ai

Third-party skill for operating Railway infrastructure from agent sessions: projects, services, databases, buckets, deploys, infrastructure as code, environments, domains, metrics, feature flags, recovery, and the account signup and MCP paths.

by Railway

• Provisioning and deploying client infrastructure through an agent
• Infrastructure work that should stay conversational instead of dashboard-driven

source & install at railway.com

Local runtime skill for Laya, the open-source non-autoregressive System 1 decision engine: choice, score, and noul primitives that turn natural language and application state into typed judgments with calibrated probabilities, running locally. The Laya repo is the upstream; the model entry lists the weights.

by Braydon

built on Laya by NandhaKishorM; the runtime skill is my guide to the local MPS install

• Fast local classification, gating, and triage steps without an API call
• The open build path when a judgment step must run offline

source & install at github.com/NandhaKishorM/laya

Operating skill for herdr, the open-source pane-based agent multiplexer: dispatch and briefing templates, push-based completion protocol, review gates, and a verification ladder for the worker pipeline. The upstream ships the multiplexer and its own agent skill; this one is the fleet doctrine I run on top of it.

by Braydon

built on herdr by herdrdev; I run my own fleet doctrine in place of the agent skill it ships

• Coordinating worker agents in herdr panes from inside a session
• The dispatch, review, and verification loop for a pane fleet

source & install at herdr.dev

Routes one readable Markdown file into a focused review surface in a terminal split, collects anchored comments and suggested edits from a human reviewer, and returns the validated result to the agent. Built on the Subspace TUI through herdr or tmux.

by spacedock-dev

ships with Subspace from spacedock-dev; the installed copy runs the upstream scripts with a Pi-facing skill doc trimmed to herdr and tmux

• Human review of agent-written documents without leaving the terminal
• Collecting anchored feedback a model can act on

source & install at github.com/spacedock-dev/subspace

Builds single-file HTML slide decks: brand-ready templates, minimal navigation, a narrative engine with proven storytelling structures, and generated media for slide visuals. Used for client decks and workshop material.

by Braydon

• Client-ready decks an agent drafts and revises
• Workshop and talk material in one portable file

installed with your engagement

Builds single-file HTML white papers with print-optimized layout, narrative arcs, communication frameworks, and SVG diagrams for research, strategy, and thought-leadership content.

by Braydon

• Research reports and strategic deliverables that print clean
• Long-form positioning an agent structures and drafts

installed with your engagement

Web research through the Perplexity API: authentication, search strategy, and structured output patterns an agent can interpret, so research sweeps return evidence instead of prose.

by Braydon

• Research sweeps that need citations and structure
• Background briefs assembled inside a working session

installed with your engagement

Bash-script wrappers over the GitHub API: issues, pull requests, repository search, and state updates an agent runs without hand-writing API calls.

by Braydon

• Issue and PR workflows driven from agent sessions
• Repository research across an organization

installed with your engagement

Bash-script wrappers over Linear's GraphQL API: issue creation from conversations, work-item tracking, and project status queries.

by Braydon

• Turning conversations into tracked work items
• Project status queries without leaving the session

installed with your engagement

Investigation method for incidents, regressions, recurring problems, and surprising metrics: evidence collection, causal chains, and postmortem discipline an agent runs before anyone proposes a fix.

by Braydon

• Incident reviews that end in root cause, not blame
• Recurring problems investigated systematically instead of patched again

installed with your engagement

Scenario planning with worldview elicitation, external scenario construction, and actor-relative impact analysis, documented so decisions under uncertainty get reasoned futures instead of a single forecast.

by Braydon

• Strategy decisions that deserve more than one future
• Preparedness and positioning work with explicit assumptions

installed with your engagement

Finds and removes dead code, duplicates, and quality issues with archive-based safety: multi-signal detection, then a two-stage review before anything is deleted.

by Braydon

• Codebase cleanups an agent runs with a safety net
• Paying down cruft before a handoff or audit

installed with your engagement

Scripted browser automation for real web tasks: form filling, multi-step flows, data extraction, and reusable automation scripts when a task needs a real browser.

by Braydon

• Web workflows too structured for manual clicking and too real for an API
• Reusable automation an agent writes and reruns

installed with your engagement

Drives the Workgraph task system from the shell: the verified verbs for listing, claiming, logging, completing, and failing tasks, plus inbox coordination and daemon checks. wg is open source; the upstream points at its repo, and the Workgraph bridge entry covers the in-harness tools.

by Braydon

built on wg by graphwork; I wrote the reference skill for its shell verbs

• Task-graph operations from any terminal or agent session
• Agent coordination through task inboxes

source & install at github.com/graphwork/wg

Intelligent workspace cleanup using multi-signal detection (similarity, timestamps, references) to identify clutter, with a two-stage safety review before archiving anything.

by Braydon

• Reclaiming project directories without deleting the wrong thing
• Pre-handoff tidy-ups with an audit trail

installed with your engagement

Ports agent workflows into Gemini CLI extensions: extension layout, context files, command patterns, and guardrails enforced with tests, CI, and pre-commit hooks.

by Braydon

• Moving a proven agent workflow onto a second harness
• Multi-harness delivery when a team runs mixed tooling

installed with your engagement

Manages Apple Reminders through MCP: list organization, reminder creation and updates, search, and tie-ins to productivity workflows.

by Braydon

• Personal task capture an agent handles end to end
• Keeping reminder lists organized without manual sorting

installed with your engagement

Multi-provider image and video generation workflows through the grok CLI: make commands, provider-specific generation, async task tracking, clip stitching, and output evaluation. Wired to generation APIs through local tooling with no public repo, so it installs with an engagement.

by Braydon

• Campaign and deck visuals generated in batch
• Video clips assembled from generated segments

installed with your engagement

Zero-config WireGuard mesh VPN (open-source clients over a hosted coordination plane) that puts every host I run on one private tailnet with stable 100.x addresses.

by Tailscale

• Private tailnet dev previews: share a build at a stable 100.x address (e.g. 100.68.255.106:8183) with no public exposure
• One flat network across laptops, dev boxes, and cloud hosts, reachable from desktop and mobile anywhere

source & install at tailscale.com

Cross-platform desktop SSH client with hosts, keys, and snippets synchronized across devices.

by Termius

• Day-to-day SSH from the desktop into my hosts and client hosts on the tailnet
• Keeping host and key inventory in sync across machines instead of per-device ssh_config sprawl

source & install at termius.com

iOS terminal over SSH, Mosh, and ET built for driving remote hosts and coding-agent sessions from a phone; tmux-aware, so mobile attaches to the same panes the desktop sees.

by Moshi

• Attaching to tmux agent-fleet sessions from a phone over Mosh (roaming-friendly; survives network switches)
• Checking on long-running agent work away from the desk

source & install at getmoshi.app

A personal knowledge store with notes, daily notes, collections, and search behind a local app, CLI, and MCP server, installed and operated in your environment.

by Braydon

• Replacing scattered notes with one queryable knowledge base an agent can read and write
• Engagements that need a shared client knowledge store

installed with your engagement

A local email-and-message archive service: synced mail on your own storage, a supervised daemon, and CLI and MCP search so agents can query message history without cloud APIs.

by kenn-io

• Executives who want their message history queryable but self-hosted
• Engagements needing email-derived intelligence with data staying on-prem

source & install at github.com/kenn-io/msgvault

A Workgraph-backed task board for agent work: claiming, status, comments, planning, and handoff between humans and agent workers on one surface.

by Braydon

• Coordinating a mixed human and agent workforce on real task queues
• Giving an executive one pane over everything the agents are doing

installed with your engagement

Meeting capture and tooling service exposed to agents over MCP: calendar-aware meeting workflows, prep, and follow-through that run where the calendar lives.

by Braydon

• Executives whose meeting prep and follow-up should run itself against their calendar
• Engagements building calendar-aware agent workflows

installed with your engagement

Recurring expert-ensemble panels (practitioner, buyer-voice, and adversarial seats) that pressure-test strategy, drafts, and workshop design before anything goes to a real audience.

by Braydon

• Pressure-testing positioning, pricing, and drafts against buyer reaction
• Recurring design review without hiring a standing committee

installed with your engagement

Intent-accountable collectives of model-based intelligence: one shared intent per collective, live headless agent teams running as persistent sessions, and a light operator plane with explicit grants and a human-only kill switch. The fleet builds and improves itself toward the operator's stated qualities.

by Braydon

• Standing up a client's own intent-accountable agent collective
• Engagements that need persistent, self-directed agent teams with explicit authority boundaries

installed with your engagement