Head to head · Multi-agent orchestration · October 2026 research run
herdr vs Letta
herdr scores 71.1 (BB) on agent readiness against Letta's 63.5 (B), and leads in 5 of 7 scored categories. Letta leads on maintenance & community. Both do multi-agent orchestration.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Best memory layers for AI agents · All 383 memory comparisons
Which one, for what
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
- Reliability, 65 against 58
- Schema & documentation, 91 against 70
- Agent ergonomics, 73 against 67
- Security & auth, 49 against 35
- Transparency & trust, 70 against 55
Also in its favour
- Agent-ready, a grade of BB or better
- 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
Letta B
Best for Long-lived coding agents and assistants that keep memory and identity across sessions and machines.
Ahead on
- Maintenance & community, 85 against 63
Also in its favour
- Runs on your own machine
Watch for
The default permission mode is unrestricted, the renamed bypassPermissions, so tool calls aren't confirmed unless the user picks another mode
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.
Maintenance & community Letta +22
herdr 63
v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63.
Letta 85
v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.
Schema & documentation herdr +21
herdr 91
Read as a CLI and socket API. herdr api schema --json prints a JSON Schema for requests, responses, errors and events, also at docs/next/api/herdr-api.schema.json (25). Markdown for agents, with skills/herdr/SKILL.md and distribution/agent-guide.md. https://herdr.dev/llms.txt indexes the 0.9.5 docs as raw source files for agents (10). The skill says when to use herdr and when not to, and the socket docs say which layer to use for which job, but the schema itself carries few descriptions (15). The schema has 49 enums and agent names are constrained by a pattern, while some inputs are free strings (12). Many CLI and JSON examples, a documented error shape with codes such as not_found, agent_blocked and events_lost (14). Versioned docs per release and a changelog (15). 25 + 10 + 15 + 12 + 14 + 15 = 91.
Letta 70
Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an applies_to block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.
Transparency & trust herdr +15
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.
Letta 55
Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55.
Security & auth herdr +14
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.
Letta 35
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 injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is unrestricted; standard, acceptEdits and strict are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.
Reliability herdr +7
herdr 65
Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65.
Letta 58
Local-software lines, read for the harness. @letta-ai/letta-code on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.
Agent ergonomics herdr +6
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.
Letta 67
Harness reading. Toolsets switch with /model, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). letta -p --output-format json for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.
Score by category
| Category | Weight | herdr | Letta | Edge |
|---|---|---|---|---|
| Reliability | 16% | 65 | 58 | herdr +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 91 | 70 | herdr +21 |
| Agent ergonomics | 13% | 73 | 67 | herdr +6 |
| Security & auth | 14% | 49 | 35 | herdr +14 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 63 | 85 | Letta +22 |
| Transparency & trust | 7% | 70 | 55 | herdr +15 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 71.1/100 | B 63.5/100 |
Facts side by side
| Fact | herdr | Letta |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | herdr | Letta |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio | |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-14 | 2026-11-06 |
| Terms last updated | no document linked | no date given |
| Privacy policy last updated | 2026-11-02 | no date given |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 52k stars | 3.8k stars, 86k npm/wk, 2.2k PyPI/wk |
How the scores have moved
Verdicts
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.
Letta
Letta's open-source harness gives agents git-tracked memory blocks, skills, subagents and headless JSON runs, with a $0 plan and public per-agent API prices. It starts in the unrestricted permission mode, defaults to Letta Cloud, sends usage telemetry unless LETTA_CODE_TELEM=0 is set, and the V1 API server the comparisons describe is retired.
Before you call either
herdr
- Check
HERDR_ENV=1before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop - Use
herdr agent prompt <name> --waitrather than a separate prompt and wait, so a fast agent can't finish between the two calls - If a wait times out or stalls, read the pane with
herdr agent readbefore sending the prompt again, since it may have been delivered - If an agent is
blocked, show the person the dialogue and let them answer it - Close only the panes, tabs and workspaces you created, unless the person asks otherwise
Letta
- Start headless runs with an explicit permission mode such as
standardorstrict; the default auto-approves tools - Pass
--backend localfor work that must stay on the machine, since Letta Cloud is the default - Set LETTA_CODE_TELEM=0 in unattended runs if usage events must not be sent
- Use
letta -p --output-format jsonfor scripted runs and parse the JSON, not the terminal output - Don't plan on the retired V1 REST server or
.afAgentFile import; both are gone
Questions
Which is better for AI agents, herdr or Letta?
herdr scores 71.1 (BB) on agent readiness against Letta's 63.5 (B), and leads in 5 of 7 scored categories. Letta leads on maintenance & community.
Are herdr and Letta open source?
Yes. herdr is open source (Apache-2.0). Letta is open source (Apache-2.0).
Other comparisons with herdr or Letta
- Agent Zero vs Letta
- Aider vs Letta
- Amp vs Letta
- Antigravity CLI vs Letta
- Auggie CLI vs Letta
- AXLR vs Letta
- boxes.dev vs Letta
- Claude Code vs Letta
- Click vs Letta
- Cline vs Letta
- Conductor vs Letta
- Crush vs Letta
- Cursor CLI vs Letta
- DeepSeek Harness (dsh) vs Letta
- dsh-superagent (DeepSeek) vs Letta
- Devin vs Letta
- Droid CLI vs Letta
- Pi vs Letta
- Emdash vs Letta
- Gemini CLI vs Letta
- GitHub Copilot CLI vs Letta
- goose vs Letta
- Harness² vs Letta
- HarnessRouter vs Letta
- Jules vs Letta
- Junie CLI vs Letta
- Kilo Code CLI vs Letta
- Kimi Code CLI vs Letta
- Kiro CLI vs Letta
- Letta vs mini-swe-agent
- Letta vs MiniMax Code
- Letta vs Mistral Vibe CLI
- Letta vs Muse Code
- Letta vs OpenAI Agents API
- Letta vs OpenAI Codex
- Letta vs OpenCode
- Letta vs OpenHands
- Letta vs OpenMausBot
- Letta vs Orca
- Letta vs Paseo
- Letta vs Prime Agent
- Letta vs Qoder CLI
- Letta vs Qwen Code
- Letta vs Mirror CLI
- Letta vs Rovo Dev CLI
- Letta vs Sculptor
- Letta vs T3 Code
- Letta vs Traycer
- Letta vs Unstoppable
- Letta vs Verdent
- Letta vs Vibe-Trading
- Letta vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs herdr
- Agent Relay vs Letta
- Amp vs herdr
- Antigravity CLI vs herdr
- Auggie CLI vs herdr
- AXLR vs herdr
- boxes.dev vs herdr
- Claude Code vs herdr
- Clawboo vs herdr
- Clawboo vs Letta
- CLI Manager vs herdr
- CLI Manager vs Letta
- Cline vs herdr
- Conductor vs herdr
- Crush vs herdr
- DeepSeek Harness (dsh) vs herdr
- dsh-superagent (DeepSeek) vs herdr
- Devin vs herdr
- Droid CLI vs herdr
- Emdash vs herdr
- Friday vs herdr
- Friday vs Letta
- Gemini CLI vs herdr
- GitHub Copilot CLI vs herdr
- goose vs herdr
- Harness vs herdr
- Harness vs Letta
- HarnessRouter vs herdr
- herdr vs Jules
- herdr vs Junie CLI
- herdr vs Kilo Code CLI
- herdr vs Kimi Code CLI
- herdr vs Kiro CLI
- herdr vs MiniMax Code
- herdr vs Mistral Vibe CLI
- herdr vs Muse Code
- herdr vs OpenCode
- herdr vs OpenHands
- herdr vs OpenMausBot
- herdr vs Orca
- herdr vs Paperclip
- herdr vs Parallax
- herdr vs Paseo
- herdr vs Prime Agent
- herdr vs Qoder CLI
- herdr vs Qwen Code
- herdr vs Mirror CLI
- herdr vs Rovo Dev CLI
- herdr vs Sculptor
- herdr vs T3 Code
- herdr vs Traycer
- herdr vs Unstoppable
- herdr vs Verdent
- herdr vs Vibe-Trading
- herdr vs Warp (Warp Agent CLI and the Oz Agent API)
- Letta vs Paperclip
- Letta vs Parallax
Machine-readable
- This page as Markdown
/compare/herdr-vs-letta.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/herdr.json·/api/v1/tools/letta.json - From a terminal
anchor compare herdr letta(the CLI) - Over MCP
compare_tools {"a": "herdr", "b": "letta"}at/mcp, no key