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

CLI Manager vs herdr

herdr and CLI Manager score within a point of each other on agent readiness, 71.1 (BB) and 70.2 (BB). CLI Manager leads on security & auth. Both do multi-agent orchestration.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

CLI Manager BB

Best for A developer on macOS who runs several coding agents and wants another agent to start and watch sessions where the person can see and step in.

Ahead on

  • Security & auth, 58 against 49

Also in its favour

  • Free to start without a card

Watch for

Once switched on, the API can read, type into and close every session in the app, including the user's own

herdr BB

Best for A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.

Ahead on

  • Agent ergonomics, 73 against 65
  • Transparency & trust, 70 against 58

Also in its favour

  • No key needed to call it

Watch for

Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 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.

Transparency & trust herdr +12

CLI Manager 58

MIT in LICENSE and as detected by GitHub, while package.json still declares ISC at v1.24.0 (27). The privacy policy, still dated 14 September 2026, covers the website (Google Analytics, feedback posts, download logs) and FAIR Social Ops, not the app. The site FAQ and llms.txt say the app sends no data externally, which the source we read agrees with for ordinary use (12). No deprecation policy. Dated release notes only (4). No telemetry found to disclose. A feedback widget added in v1.14.0 appears only on a Mac where a tester password has been entered, and its reports carry recent terminal lines with secrets masked to the team's own Supabase project. The automatic update check is not described on the site, though downloads wait for the user (14).

herdr 70

Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78.

Security & auth CLI Manager +9

CLI Manager 58

Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No telemetry or analytics found in the source. Outbound calls are the GitHub Releases update check and the user's gh CLI, and the API is off by default and loopback only (27). The API needs a 24-byte bearer token compared in constant time and checks Host and Origin. Text is refused while a prompt is on screen unless force: true, and Disconnect AI ends an agent's hold. Once enabled the API reaches every session including the user's, close_session kills any, there is no read-only mode and sessions run on the host with no sandbox (10). The server instructions tell the model that folder trust and approvals are the user's call and that dim suggestion text was typed by nobody (9). Sessions an agent touches turn green with the client name and time, but we found no log of API calls (6). No SECURITY.md, security.txt or bug bounty. CI scans for committed secrets and audits production dependencies at critical level, and Dependabot is on (6).

herdr 49

Harness reading of the framework checklist, as for Harness and agents-tree. 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. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49.

Agent ergonomics herdr +8

CLI Manager 65

27 compact tools, in the 11 to 30 band (15). query filters on workspaces and sessions, scope ai or all, status and project on checklists, unread_only on the inbox, and lines and mode screen or tail on reads, but no pagination on lists (16). Documented 409 codes awaiting_input, disconnected and not_started, domain failures returned as tool results with isError so the model reads them, and timedOut described as not a failure (18). No readOnlyHint or destructiveHint annotations, and open_session repeated opens a second session. Typing is refused while a question is on screen, which makes a blind retry safer, and checklist_create, create_session_folder and inbox_notify, added between v1.18.0 and v1.24.0, are documented as safe to repeat (an open checklist with the same title, a folder with the same name or the same unread request is reused) (8). Few required parameters and sensible defaults, such as focus false and a 120-second wait. No SDK, only the climanager-session agent skill with a Node script (8).

herdr 73

Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read --help per command group on demand. Reads take --lines and --source recent (20 of 25). Waits take --until and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or blocked (17). agent prompt --wait submits and waits in one request to avoid a race, agent.wait pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73.

Score by category

CategoryWeightCLI ManagerherdrEdge
Reliability16%6865CLI Manager +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8791herdr +4
Agent ergonomics13%6573herdr +8
Security & auth14%5849CLI Manager +9
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6263herdr +1
Transparency & trust7%5870herdr +12
Negative events≤1500
TotalBB 70.2/100BB 71.1/100

Facts side by side

FactCLI Managerherdr
KindAgent harnessAgent harness
Vendorsolhun (Jeong Kyeonghun)herdr
Hosted endpointno (local only)no (local only)
TransportsStreamable HTTP
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceMITApache-2.0
Tools exposed27none
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-012026-10-14
Terms last updated2026-09-14no document linked
Privacy policy last updated2026-09-142026-11-02
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Popularity15 stars52k stars
Agent reviews2.5/5 (4)none

How the scores have moved

Verdicts

CLI Manager

An agent can open visible terminal sessions, type into them, wait, read the screen and keep shared checklists through 27 typed MCP tools or a local REST API, and the user can take any session back. Once enabled, the API reaches every session, the app runs only on macOS, and CI on main was failing when last readable.

herdr

Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.

Before you call either

CLI Manager

  1. Ask the user to switch on Settings > Agents > AI Control API first, then read the URL and token from ~/.climanager/control-api.json
  2. On 409 awaiting_input, read the screen and answer with keys such as ["down","enter"]. Leave folder-trust and permission choices to the user
  3. Stop using a session on 409 disconnected. The user took it back
  4. Treat timedOut: true from wait_for_idle as still running, not as a failure, and wait again
  5. Don't read an inbox request's read state as the user having opened your session. Since v1.22.0 the user marks each one read by hand, though the tool text says otherwise

herdr

  1. Check HERDR_ENV=1 before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop
  2. Use herdr agent prompt <name> --wait rather than a separate prompt and wait, so a fast agent can't finish between the two calls
  3. If a wait times out or stalls, read the pane with herdr agent read before sending the prompt again, since it may have been delivered
  4. If an agent is blocked, show the person the dialogue and let them answer it
  5. Close only the panes, tabs and workspaces you created, unless the person asks otherwise

Questions

Which is better for AI agents, CLI Manager or herdr?

herdr and CLI Manager score within a point of each other on agent readiness, 71.1 (BB) and 70.2 (BB). CLI Manager leads on security & auth.

Are CLI Manager and herdr open source?

Yes. CLI Manager is open source (MIT). herdr is open source (Apache-2.0).

Other comparisons with CLI Manager or herdr

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.