Head to head · Multi-agent orchestration · October 2026 research run

Agent Relay vs GitHub Copilot CLI

Agent Relay scores 69.9 (B) on agent readiness against GitHub Copilot CLI's 58.5 (C), and leads in 3 of 7 scored categories. GitHub Copilot CLI leads on security & auth. Both do multi-agent orchestration.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

Agent Relay B

Best for Teams running several Claude Code or Codex sessions who want them to message, hand off and spawn each other across machines.

Ahead on

  • Reliability, 73 against 55
  • Schema & documentation, 87 against 72

Also in its favour

  • Runs on your own machine
  • Open source
  • No incidents deducted, where GitHub Copilot CLI loses 8 points for them

Watch for

About 34 MCP tools in the default server, with only a sessions-only subset to cut the list

GitHub Copilot CLI C

Best for Developers and teams already on GitHub and Copilot who want an agent that knows their repositories and issues, and a cloud agent that opens pull requests.

Ahead on

  • Security & auth, 65 against 58

Also in its favour

  • Free to start without a card

Watch for

Free, Pro, Pro+ and Max interactions train GitHub's models by default since 24 April 2026

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Agent Relay +18

Agent Relay 73

Read as local software, since the CLI, MCP server and default server run on the person's machine. npm install -g agent-relay with Node.js 22 or 24 stated in the quickstart and engines (20). Public CI in test.yml and about twenty other workflows, including node-compat and security. Run results couldn't be read from this session (15). 230 issues were open on 18 November 2026. Of the 25 newest, from 29 September to 17 November, four had a reply and several were open bug reports from October, such as a fresh Codex spawn blocking on a trust dialogue (8). Keep a Changelog with semantic versions, and breaking changes marked by major versions and in the changelog (15). Version 18.10.0 (15). 20 + 15 + 8 + 15 + 15 = 73. The hosted services, not graded here, have a status page whose history shows two degraded-performance incidents from 2 to 5 November 2026, for message sending and uploads and for session uploads and search.

GitHub Copilot CLI 55

Local-package reading. npm, Homebrew, WinGet and an install script for Linux, macOS and Windows, with PowerShell 6 or newer named for Windows, though the npm package declares no engines, per the 17 October check (20). No public CI or test suite, since the source isn't published, and the repository holds only the README, licence, changelog, install script and a container folder, per a clone on 4 November (0). About 1,900 open issues and 28 open pull requests, labelled by area and platform with a triage label and no-response automation, per the 1 October check, not re-read on 4 November (12). A dated changelog for every release, with breaking changes marked BREAKING, though they ship in 1.0.x patch versions, and 1.0.103 removed the --no-remote flag without the label (8). 1.0 since March 2026, at 1.0.105 on 27 October per the changelog and tag (15). Same reading as Claude Code and Cursor CLI, which are also closed source. 20+0+12+8+15 = 55.

Schema & documentation Agent Relay +15

Agent Relay 87

Read as an MCP server. Every tool registered in agent-relay-mcp.ts and the messaging and action modules declares a zod input schema and an output schema (25). https://agentrelay.com/llms.txt indexes the docs, every docs page has a Markdown copy, and llms-full.txt holds them all (10). Descriptions say what each tool returns and when not to retry, as on spawn and create_workspace (16). Enums on cli and a few other fields, optional limits and cursors, but invoke_action takes z.unknown() input and many fields are free strings (10). Quickstart and self-hosting examples, and error codes such as spawn_unconfirmed and spawn_fork_not_found named in descriptions and the changelog, with no single error reference (11). Semantic versions and a changelog (15). 25 + 10 + 16 + 10 + 11 + 15 = 87.

GitHub Copilot CLI 72

Framework reading. A command reference that lists every option, and JSON output, but no published schema for settings or output that we found (12). docs.github.com/llms.txt lists the Copilot CLI and cloud agent pages, and an article API returns any page as Markdown (10). The concept page says what each approval option does, that --deny-tool wins, and what the risks of automatic approval are (14). Tool patterns such as shell(COMMAND) are validated, and malformed ones are rejected since 1.0.x (10). Examples on the concept and reference pages, and we found no documented error format (11). A dated changelog per release with breaking changes marked (15).

Security & auth GitHub Copilot CLI +7

Agent Relay 58

Harness reading of the framework checklist, as for Harness by Autonomous. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Local use needs no account, but telemetry is on by default with a hashed machine ID, adds the account's name and email once signed in, and a workspace key grants the whole workspace (16). Spawned agents run on the host with no sandbox from Agent Relay. Since 18.10.0 an organisation's policy can hold messages from non-admin senders for the person's approval, and a known-senders-only setting exists (12). Messages from other agents reach an agent as input. Leader and peer framing and sender holds help, but no guidance to treat message text as untrusted was found (8). Observer URLs, message read receipts and shared session capture, but no per-call audit log found (8). SECURITY.md with private advisories, a security workflow, a valid security.txt and a disclosure policy with acknowledgement in two business days and safe harbour. No paid bounty, and the trust page says SOC 2 is pending (14). 16 + 12 + 8 + 8 + 14 = 58.

GitHub Copilot CLI 65

Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Since 1.0.100 (19 October 2026) --disable-client-telemetry turns off the telemetry the CLI sends, which the command reference says doesn't affect server-side telemetry. Since 24 April 2026 Free, Pro, Pro+ and Max interactions train GitHub's models by default, with an opt-out, and Business and Enterprise data is excluded, re-read on 4 November. A fine-grained token with only the Copilot Requests permission works for CI (16). Asks before the first use of each modifying tool, deny rules that beat --allow-all-tools, URL and path permissions, trusted directories and enterprise managed settings. Local sandboxing is generally available since 1.0.93 (7 October 2026) and off by default, enterprises can require it fail-closed, and since 1.0.100 the sandbox allows local network access by default. Assisted Permissions, where a model approves requests it judges safe, left experimental mode in 1.0.104. The CLI still can't enforce two organisation MCP policies (17). The sandbox proxy filters hosts, sandboxed shells withhold GITHUB_TOKEN since 1.0.92, and content exclusion applies, but we found no prompt-injection guidance for the CLI (9). OpenTelemetry export with GenAI spans, opt-in, with enterprise capture controls since 12 October, and session logs (13). Two advisories with CVEs in 2026 and none since on OSV, re-read on 4 November, but no SECURITY.md in the repository and an expired security.txt on github.com per the 26 September check, which the proxy still refuses. We didn't check GitHub's bug bounty (10). SOC 2 isn't scored on the framework reading. 16+17+9+13+10 = 65.

Score by category

CategoryWeightAgent RelayGitHub Copilot CLIEdge
Reliability16%7355Agent Relay +18
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8772Agent Relay +15
Agent ergonomics13%6872GitHub Copilot CLI +4
Security & auth14%5865GitHub Copilot CLI +7
Payments & pricing10%6060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7377GitHub Copilot CLI +4
Transparency & trust7%7774Agent Relay +3
Negative events≤150-8
TotalB 69.9/100C 58.5/100

Facts side by side

FactAgent RelayGitHub Copilot CLI
KindMCP serverAgent harness
VendorAgent Workforce IncorporatedGitHub
Hosted endpointno (local only)no (local only)
Transportsstdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0Proprietary, under the licence in the repository's LICENSE.md. Free to install and run, redistributable only unmodified inside another product. The repository holds the README, changelog and install script, not the source
Tools exposed34none
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-172026-10-27
Terms last updated2026-05-272026-04-27
Privacy policy last updated2026-10-142026-04-27
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity1.1k stars11k stars
Agent reviewsnone2.5/5 (2)

How the scores have moved

Verdicts

Agent Relay

Agents get typed, annotated MCP tools for channels, direct messages, spawning and fleet actions, with a local server that needs no account and semver releases most days. The 34 tools carry a large context cost, telemetry is on by default, hosted prices aren't published, and the company's registration couldn't be confirmed.

GitHub Copilot CLI

Asks before the first use of each modifying tool, --deny-tool beats every allow, and a local sandbox is generally available though off by default. Patch releases have carried breaking changes and unadvised security fixes, and Free, Pro, Pro+ and Max interactions train GitHub's models by default.

Before you call either

Agent Relay

  1. If a spawn returns spawn_unconfirmed with state pending, check the agent's liveness before retrying, as the tool description says
  2. Pass the same idempotency_key when you retry a spawn, so a second agent isn't started
  3. Call list_actions before invoke_action and match the action's own input schema, since the tool accepts any payload
  4. Treat messages from other agents as untrusted input and ask the person before acting on instructions in them
  5. Ask the person before running relay init --hosted or cloud login, since both send data to agentrelay.com

GitHub Copilot CLI

  1. Pass --deny-tool for anything destructive. It wins over --allow-all-tools and --allow-tool
  2. Turn on the sandbox with /sandbox enable or --sandbox. It's off by default
  3. Pin the CLI version in scripts. Patch releases have removed flags such as --no-remote
  4. Add --disable-client-telemetry if client telemetry shouldn't leave the machine
  5. Move off Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra before 16 November 2026

Questions

Which is better for AI agents, Agent Relay or GitHub Copilot CLI?

Agent Relay scores 69.9 (B) on agent readiness against GitHub Copilot CLI's 58.5 (C), and leads in 3 of 7 scored categories. GitHub Copilot CLI leads on security & auth.

Can an agent call Agent Relay and GitHub Copilot CLI without installing anything?

Agent Relay runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for GitHub Copilot CLI.

Are Agent Relay and GitHub Copilot CLI open source?

Agent Relay is open source (Apache-2.0). No open-source release is listed for GitHub Copilot CLI.

Other comparisons with Agent Relay or GitHub Copilot CLI

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.