THEDE TECHNOLOGIES
Revised 19 Nov 2026

Feed it, staff it, sell it, sheet 13 of 13

Agent harnesses

The loop around the model: tools, permissions, context, memory, sub-agents and scheduled runs, the choice between adopting a coding agent and building your own, and running several at once.

23Tools I checked
5Open gaps
Many choices, few standardsWhere the market is
19 Nov 2026Last checked
If you do one thing

Keep your house rules in AGENTS.md and your permissions in one written policy, so the harness you pick today is easy to change next quarter.

The toolkit as a map: 4 layers, 13 sheets, 112 tools drawn as filled squares and 46 open gaps drawn as hatched squares INDEX TO THE THIRTEEN SHEETS 112 tools, 46 open gaps, revised 19 Nov 2026 LAYER 1 TRUST THE OUTPUT Layer total 3 sheets 22 tools on the map 11 open gaps 01 Observability and evals promptfoo 1 promptfoo Langfuse 2 Langfuse Arize Phoenix 3 Arize Phoenix Braintrust 4 Braintrust DeepEval 5 DeepEval OpenTelemetry GenAI conventions 6 OTel GenAI Demystifying evals for AI agents 7 Evals guide OpenAI deprecations 8 OpenAI dates Judge calibration 9 Judge kappa Open gap a a Open gap b b Open gap c c Open gap d d 02 The door before the merge GitHub branch protection and CODEOWNERS 1 Branch rules GitHub Copilot code review 2 Copilot review Claude Code Review 3 Claude Review Greptile 4 Greptile CodeRabbit 5 CodeRabbit Socket Firewall 6 Socket Firewall GitHub Agentic Workflows 7 Agentic Workflows Open gap a a Open gap b b Open gap c c Open gap d d 03 Measuring the org DORA, State of AI-assisted Software Development 2025 1 DORA 2025 METR, early-2025 AI and experienced developers 2 METR study DX AI Measurement Framework 3 DX GitClear code quality research 4 GitClear Faros 5 Faros Multitudes 6 Multitudes Open gap a a Open gap b b Open gap c c LAYER 2 CONTAIN THE AGENT 4 sheets, 35 tools, 13 gaps 04 MCP gateways and registries MCP specification, 2026-07-28 1 MCP spec Official MCP Registry 2 MCP Registry Docker MCP Gateway 3 Docker Gateway Obot 4 Obot Microsoft MCP Gateway 5 Microsoft gateway Mintive 6 Mintive Kong AI Gateway 7 Kong Cloudflare MCP server portals 8 Cloudflare portals Amazon Bedrock AgentCore Gateway 9 AgentCore Gateway Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e 05 Identity and secrets Okta Cross App Access 1 Cross App Access Auth0 Token Vault 2 Token Vault Microsoft Entra Agent ID 3 Entra Agent ID Aembit 4 Aembit Teleport 5 Teleport SPIFFE 6 SPIFFE Open gap a a Open gap b b 06 Shadow AI and ghost jobs Nudge Security 1 Nudge Harmonic Security 2 Harmonic Reco 3 Reco Microsoft Purview for AI 4 Purview Healthchecks.io 5 Health checks Cronitor 6 Cronitor Sentry Crons 7 Sentry Crons Open gap a a Open gap b b Open gap c c 07 Sandboxing and containment Claude Code sandbox 1 Claude Code sandbox Codex sandboxing 2 Codex nono 3 nono Docker Sandboxes 4 Docker Sandboxes E2B 5 E2B Hosted sandboxes 6 Hosted sandboxes Apple container 7 Apple container Anthropic Sandbox Runtime 8 Sandbox Runtime Agent hooks 9 Agent hooks Claude Code managed settings 10 Managed settings How we built Claude Code auto mode 11 Auto mode The lethal trifecta 12 Lethal trifecta OWASP LLM06: Excessive Agency 13 OWASP LLM06 Open gap a a Open gap b b Open gap c c LAYER 3 PAY FOR IT Layer total 2 sheets 13 tools on the map 7 open gaps 08 Spend governance Claude plans and pricing 1 Claude plans Claude Code cost controls 2 Claude Code costs GitHub budgets and alerts 3 GitHub budgets LiteLLM 4 LiteLLM Cloudflare AI Gateway 5 Cloudflare AI Gateway Vantage for Anthropic 6 Vantage Open gap a a Open gap b b Open gap c c Open gap d d 09 Routing and model lifecycle Anthropic model deprecations 1 Claude dates OpenRouter Auto Router 2 OpenRouter Auto Microsoft Foundry model router 3 Foundry router Amazon Bedrock intelligent prompt routing 4 Bedrock routing Not Diamond 5 Not Diamond Requesty 6 Requesty RouteLLM 7 RouteLLM Open gap a a Open gap b b Open gap c c LAYER 4 FEED IT, STAFF IT, SELL IT 4 sheets, 42 tools, 15 gaps 10 Context layer and memory Glean 1 Glean Onyx 2 Onyx Credal 3 Credal Dust 4 Dust msgvault 5 msgvault AGENTS.md 6 AGENTS .md Mem0 7 Mem0 Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e 11 Hiring and verification Greenhouse Real Talent 1 Greenhouse Real Talent Pindrop 2 Pindrop Karat 3 Karat CoderPad 4 CoderPad Open gap a a Open gap b b 12 Discovery and selling first User Interviews 1 User Interviews Respondent 2 Respondent Boardy 3 Boardy Happenstance 4 Happen stance Clay 5 Clay Listen Labs 6 Listen Labs Synthetic Users 7 Synthetic Users Synthetic Users: If, When, and How to Use AI-Generated Research 8 NN/g article Open gap a a Open gap b b Open gap c c 13 Agent harnesses Claude Code 1 Claude Code OpenAI Codex 2 Codex Gemini CLI 3 Gemini CLI GitHub Copilot agents 4 Copilot agents Cursor 5 Cursor OpenCode 6 OpenCode Goose 7 Goose Cline 8 Cline Pi, and its fork omp 9 Pi Claude Agent SDK 10 Claude Agent SDK OpenAI Agents SDK 11 OpenAI Agents SDK Google Agent Development Kit 12 Google ADK Microsoft Agent Framework 13 Agent Framework Strands Agents 14 Strands LangGraph 15 LangGraph Effective harnesses for long-running agents 16 Harness guide Paradev, formerly Superset 17 Paradev Orca 18 Orca Herdr 19 Herdr Paseo 20 Paseo Symphony 21 Symphony Stripe Minions 22 Stripe Minions StrongDM's software factory 23 StrongDM factory Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e The toolkit as a map: 4 layers, 13 sheets, 112 tools drawn as filled squares and 46 open gaps drawn as hatched squares INDEX TO THE THIRTEEN SHEETS 112 tools, 46 open gaps, revised 19 Nov 2026 LAYER 1 TRUST THE OUTPUT Layer total 3 sheets 22 tools on the map 11 open gaps 01 Observability and evals promptfoo 1 promptfoo Langfuse 2 Langfuse Arize Phoenix 3 Arize Phoenix Braintrust 4 Braintrust DeepEval 5 DeepEval OpenTelemetry GenAI conventions 6 OTel GenAI Demystifying evals for AI agents 7 Evals guide OpenAI deprecations 8 OpenAI dates Judge calibration 9 Judge kappa Open gap a a Open gap b b Open gap c c Open gap d d 02 The door before the merge GitHub branch protection and CODEOWNERS 1 Branch rules GitHub Copilot code review 2 Copilot review Claude Code Review 3 Claude Review Greptile 4 Greptile CodeRabbit 5 CodeRabbit Socket Firewall 6 Socket Firewall GitHub Agentic Workflows 7 Agentic Workflows Open gap a a Open gap b b Open gap c c Open gap d d 03 Measuring the org DORA, State of AI-assisted Software Development 2025 1 DORA 2025 METR, early-2025 AI and experienced developers 2 METR study DX AI Measurement Framework 3 DX GitClear code quality research 4 GitClear Faros 5 Faros Multitudes 6 Multitudes Open gap a a Open gap b b Open gap c c LAYER 2 CONTAIN THE AGENT 4 sheets, 35 tools, 13 gaps 04 MCP gateways and registries MCP specification, 2026-07-28 1 MCP spec Official MCP Registry 2 MCP Registry Docker MCP Gateway 3 Docker Gateway Obot 4 Obot Microsoft MCP Gateway 5 Microsoft gateway Mintive 6 Mintive Kong AI Gateway 7 Kong Cloudflare MCP server portals 8 Cloudflare portals Amazon Bedrock AgentCore Gateway 9 AgentCore Gateway Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e 05 Identity and secrets Okta Cross App Access 1 Cross App Access Auth0 Token Vault 2 Token Vault Microsoft Entra Agent ID 3 Entra Agent ID Aembit 4 Aembit Teleport 5 Teleport SPIFFE 6 SPIFFE Open gap a a Open gap b b 06 Shadow AI and ghost jobs Nudge Security 1 Nudge Harmonic Security 2 Harmonic Reco 3 Reco Microsoft Purview for AI 4 Purview Healthchecks.io 5 Health checks Cronitor 6 Cronitor Sentry Crons 7 Sentry Crons Open gap a a Open gap b b Open gap c c 07 Sandboxing and containment Claude Code sandbox 1 Claude Code sandbox Codex sandboxing 2 Codex nono 3 nono Docker Sandboxes 4 Docker Sandboxes E2B 5 E2B Hosted sandboxes 6 Hosted sandboxes Apple container 7 Apple container Anthropic Sandbox Runtime 8 Sandbox Runtime Agent hooks 9 Agent hooks Claude Code managed settings 10 Managed settings How we built Claude Code auto mode 11 Auto mode The lethal trifecta 12 Lethal trifecta OWASP LLM06: Excessive Agency 13 OWASP LLM06 Open gap a a Open gap b b Open gap c c LAYER 3 PAY FOR IT Layer total 2 sheets 13 tools on the map 7 open gaps 08 Spend governance Claude plans and pricing 1 Claude plans Claude Code cost controls 2 Claude Code costs GitHub budgets and alerts 3 GitHub budgets LiteLLM 4 LiteLLM Cloudflare AI Gateway 5 Cloudflare AI Gateway Vantage for Anthropic 6 Vantage Open gap a a Open gap b b Open gap c c Open gap d d 09 Routing and model lifecycle Anthropic model deprecations 1 Claude dates OpenRouter Auto Router 2 OpenRouter Auto Microsoft Foundry model router 3 Foundry router Amazon Bedrock intelligent prompt routing 4 Bedrock routing Not Diamond 5 Not Diamond Requesty 6 Requesty RouteLLM 7 RouteLLM Open gap a a Open gap b b Open gap c c LAYER 4 FEED IT, STAFF IT, SELL IT 4 sheets, 42 tools, 15 gaps 10 Context layer and memory Glean 1 Glean Onyx 2 Onyx Credal 3 Credal Dust 4 Dust msgvault 5 msgvault AGENTS.md 6 AGENTS .md Mem0 7 Mem0 Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e 11 Hiring and verification Greenhouse Real Talent 1 Greenhouse Real Talent Pindrop 2 Pindrop Karat 3 Karat CoderPad 4 CoderPad Open gap a a Open gap b b 12 Discovery and selling first User Interviews 1 User Interviews Respondent 2 Respondent Boardy 3 Boardy Happenstance 4 Happen stance Clay 5 Clay Listen Labs 6 Listen Labs Synthetic Users 7 Synthetic Users Synthetic Users: If, When, and How to Use AI-Generated Research 8 NN/g article Open gap a a Open gap b b Open gap c c 13 Agent harnesses Claude Code 1 Claude Code OpenAI Codex 2 Codex Gemini CLI 3 Gemini CLI GitHub Copilot agents 4 Copilot agents Cursor 5 Cursor OpenCode 6 OpenCode Goose 7 Goose Cline 8 Cline Pi, and its fork omp 9 Pi Claude Agent SDK 10 Claude Agent SDK OpenAI Agents SDK 11 OpenAI Agents SDK Google Agent Development Kit 12 Google ADK Microsoft Agent Framework 13 Agent Framework Strands Agents 14 Strands LangGraph 15 LangGraph Effective harnesses for long-running agents 16 Harness guide Paradev, formerly Superset 17 Paradev Orca 18 Orca Herdr 19 Herdr Paseo 20 Paseo Symphony 21 Symphony Stripe Minions 22 Stripe Minions StrongDM's software factory 23 StrongDM factory Open gap a a Open gap b b Open gap c c Open gap d d Open gap e e
Sheet 13: numbers are tools, letters are gapsOne sheet to the view5 tools

← → move to the next sheet over, Esc zooms out.

The problem, in plain words

A coding agent is two things: the model that does the thinking, and the harness wrapped around it. The harness is everything else. It runs the loop that lets the model call a tool and read the result, it holds the permissions, it decides what to summarize when the context fills up, it starts helpers, and it can run the whole thing on a schedule with nobody watching.

My day job is me and a staff of agents. The model is who I hired. The harness is the office I set up around them: which keys they get, the notes on the wall they read every morning, who they can hand work to, and the checklist the night shift follows. Same hire, different office, different week.

When you pick a coding agent you're mostly picking a harness, because the same model can sit inside several of them. And when you build an agent into your own product or operations, the harness is the part you're building.

Then you run more than one. Each agent gets its own copy of the code on its own branch, and the job changes from writing to supervising: which agent is working, which is done, and which has been sitting there waiting on you. A new set of apps does the supervising, and they drive the same coding agents, Claude Code and Codex among them.

Words you'll hear

Harness
The software around a model that turns it into an agent: the loop, the tools, the permissions, the memory.
Agent loop
The model asks for a tool, the harness runs it, the result goes back to the model, and it repeats until the job is done.
Compaction
Summarizing a long session when the context fills, so the agent can keep going without losing the thread.
Sub-agent
A helper the agent starts with its own context window and tools, which reports back a summary.
Hook
Your own script that runs at a fixed point, such as before a tool runs, and can stop it whatever the model decides.
Mod
Claude Code's name for a plugin whose code runs inside the harness and can watch, change or take over an event, from a tool call to the spinner. Letta Code uses the word for its own in-process code.
Skill
A packaged set of instructions and files the agent loads when a task calls for it.
Memory file
Instructions in the repo the agent reads at the start of every session, such as CLAUDE.md or AGENTS.md.
Headless run
The agent working without a person at the keyboard: from a script, in CI, or on a schedule.
Worktree
A second working copy of the same repo, on its own branch, so two agents can work at once without touching each other's files.
Fleet
Several coding agents running at once, each on its own task, watched from one place.
Software factory
Agents running the path from a ticket to a merged change, with or without a person approving the merge.

What to understand, and what to decide

Understand

Decide

Who's working on it

Every link opened on 19 Nov 2026. The numbers match the squares on the map.

Harnesses, and kits to build one

  1. Claude Code

    Product, Anthropic

    Anthropic's coding agent for the terminal, IDE and desktop, with hooks, mods, sub-agents that each get their own context window, skills, and project memory from CLAUDE.md or AGENTS.md.

    The catch. Not open source. Its licence reserves all rights, and use falls under Anthropic's commercial terms.

  2. OpenAI Codex

    Open source, Apache-2.0

    OpenAI's lightweight coding agent for the terminal, which reads AGENTS.md for project instructions.

    The catch. Its sandbox is on in the default mode. Know what full access turns off before anyone switches to it.

  3. Gemini CLI

    Open source, Apache-2.0

    Google's open-source agent that brings Gemini into the terminal, with MCP support.

    The catch. Open source means you can read what it does with your files. Somebody still has to.

  4. GitHub Copilot agents

    Product, GitHub

    GitHub's agents: a cloud agent that takes a task from a question to planned code changes and a review, and Copilot CLI in the terminal, with custom agents, skills and hooks.

    The catch. Closest to your repos and your pull requests, and so closest to one vendor. Check what leaves with you.

  5. Cursor

    Product, Cursor

    Cursor's agent for autonomous coding tasks, terminal commands and editing, in the editor, the CLI and as cloud agents, with rules, skills, sub-agents, hooks and MCP.

    The catch. Its rules and settings are Cursor's own. Keep the house rules in AGENTS.md so they outlive the editor.

  6. OpenCode

    Open source, MIT

    An open-source coding agent for the terminal.

    The catch. The project has moved GitHub organizations. Install from the current one, and pin the version.

  7. Goose

    Open source, Apache-2.0

    An open-source, extensible agent that installs, runs, edits and tests code with any LLM. Now an Agentic AI Foundation project at the Linux Foundation, alongside MCP and AGENTS.md.

    The catch. Any model means any model's habits. Your evals have to cover whichever one you plug in.

  8. Cline

    Open source, Apache-2.0

    An autonomous coding agent you can run as an IDE extension, a CLI or an SDK.

    The catch. Three ways to run it means three places to set the same permissions.

  9. Pi, omp

    Open source, MIT

    A minimal agent harness for the terminal that skips sub-agents and plan mode on purpose. You add what you need as extensions, skills and packages. omp is a fork of Pi with much more built in.

    The catch. Minimal means the missing parts are yours to build, and then yours to maintain.

  10. Claude Agent SDK

    SDK, Anthropic

    Claude Code as a library, in Python and TypeScript: the same agent loop for agents you build yourself, with cost tracking and OpenTelemetry observability.

    The catch. Build on it and the harness is yours to host, secure and keep current.

  11. OpenAI Agents SDK

    Open source, MIT

    A lightweight Python framework for multi-agent workflows.

    The catch. A framework, not a coding agent. You bring the tools, the guardrails and the hosting.

  12. Google Agent Development Kit

    Open source, Apache-2.0

    An open-source, code-first Python toolkit for building, evaluating and deploying agents.

    The catch. A kit for building agents, not a coding agent. The harness you build with it is yours to run.

  13. Microsoft Agent Framework

    Framework, Microsoft

    A framework for building agents and orchestrating multi-agent workflows, in .NET, Python and Go.

    The catch. Strongest inside Microsoft's stack. Outside it, compare it with the lighter options.

  14. Strands Agents

    Open source, Apache-2.0

    An open-source SDK for building an agent harness and controlling it end to end, in Python and TypeScript.

    The catch. Its repository was renamed to harness-sdk. Install from the current name.

  15. LangGraph

    Open source, MIT

    A low-level orchestration framework for building, managing and deploying long-running, stateful agents.

    The catch. Low-level by design. You get control, and you write more of the harness yourself.

  16. Effective harnesses for long-running agents

    Reference, Anthropic

    How an initializer agent and an incremental coding agent keep making steady progress across many context windows, built on the Claude Agent SDK.

    The catch. A model vendor writing about its own SDK. The pattern works in any harness.

Many agents at once

  1. Paradev, formerly Superset

    Open source, MIT, paid plans

    A Mac app and CLI that runs Claude Code, Codex and other coding agents side by side, each in its own git worktree and branch, with diff review in one window and an iPhone and iPad app for checking in away from the desk.

    The catch. Renamed from Superset, so older guides use the old name. The phone app comes with the paid plans.

  2. Orca

    Open source, MIT

    A desktop app for Mac, Windows and Linux that runs Claude Code, Codex and other agent CLIs in parallel, each in its own worktree, with diff comments you send back to the agent and a phone app that pings you when an agent needs you.

    The catch. It can run agents on remote servers, SSH hosts and cloud VMs. Decide where your code may go before anyone adds a host.

  3. Herdr

    Open source, Apache-2.0

    A desktop and phone app, with a separate terminal version, for coding agents on your own machines and any you reach over SSH, where each agent reports whether it's working, done or waiting on you.

    The catch. The status comes from an open protocol, OSC 7501. An agent that doesn't speak it still runs, just without a status.

  4. Paseo

    Open source, Apache-2.0

    A daemon on your machine that runs Claude Code, Codex, OpenCode, Pi and other agents, each in its own worktree if you want, with desktop, phone, web and command-line clients.

    The catch. One person maintains it full time, by its own account, with no company behind it. Weigh that before a team depends on it.

Factories, ticket to merge

  1. Symphony

    Open source, Apache-2.0

    OpenAI's spec, with an experimental Elixir reference build, for a service that reads work from an issue tracker and starts an isolated agent run for each issue. A run can end at a handoff such as human review. In OpenAI's demo the agents come back with proof of work and land the pull request once it's accepted.

    The catch. OpenAI calls it a low-key engineering preview for testing in trusted environments. Its first suggestion is to have your own coding agent build it from the spec.

  2. Stripe Minions

    Reference, Stripe

    Unattended one-shot agents, most often started from a Slack thread, each in a devbox isolated from production and the internet, with lints on every push and two rounds of CI at most. By Stripe's own count, over a thousand merged pull requests a week with no human-written code.

    The catch. A person reviews every one. The factory ends at the door before the merge.

  3. StrongDM's software factory

    Reference, StrongDM

    The boldest rules I've read: code must not be written by humans, and must not be reviewed by humans. Scenarios, often kept outside the codebase, and behavioral clones of the services it calls do the judging instead.

    The catch. One team's rule, set by the three people who started it in July 2025, on a page that also asks for at least $1,000 a day in tokens per engineer. StrongDM is now part of Delinea.

Still nobody sells

  1. A fair comparison of harnesses running the same model on the same tasks. Most benchmarks compare models.
  2. Portable configuration. Instructions move between harnesses through AGENTS.md. Permissions, hooks, skills and sub-agents don't.
  3. One permission policy enforced across every harness your engineers run.
  4. A standard way to run many agents at once. No app has won yet. Plenty of teams still wire up their own, and I built mine.
  5. A team-wide queue for agent work paused on people: what each run is waiting for, who owes the answer, and for how long. The apps show you which of your own agents are waiting.

Also on the map

I wrote about this