Head to head · Agent tracing · October 2026 research run

Agent Tree vs LangWatch

LangWatch scores 65.6 (B) on agent readiness against Agent Tree's 52.5 (D), and leads in 5 of 7 scored categories. Agent Tree leads on payments & pricing. Both do agent tracing.

Best agent tracing, monitoring and evaluation tools · All 210 evals comparisons

Which one, for what

Agent Tree D

Best for Watching and steering Claude Code sub-agents from a side pane

Ahead on

  • Payments & pricing, 60 against 40

Also in its favour

  • No key needed to call it

Watch for

Version 0.5.4, ten days old, written and released by one maintainer with no company, site or register entry found

LangWatch B

Best for Teams that want tracing, evaluations and simulated-user agent tests in one open-source product, hosted in the EU or self-hosted, and that drive it from a coding assistant through MCP or the CLI.

Ahead on

  • Reliability, 53 against 33
  • Schema & documentation, 87 against 50
  • Security & auth, 71 against 49
  • Maintenance & community, 90 against 60
  • Transparency & trust, 76 against 63

Also in its favour

  • A hosted endpoint, with nothing to install
  • Runs on your own machine
  • Free to start without a card

Watch for

The MCP server registers 101 tools, deletes and key creation among them, with no toolsets and no readOnlyHint or destructiveHint annotations in the source

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.

Schema & documentation LangWatch +37

Agent Tree 50

Framework reading, docs a model can follow, as superpowers was read. types/index.d.ts types the pane's state, and plugin.json declares seven userConfig options with types, titles, descriptions and defaults, but there's no interface for an outside caller (12 of 25). README in English and German, a nine-step GUIDE.md and PRIVACY.md, all Markdown in the repository; no llms.txt (10). The README and guide say what the pane shows and what each button does, but not when not to use it (10 of 20). Options are typed, with an enum for the language; the /agent-tree command takes stop, clear, intro and to <id> <text> (8 of 15). A demo GIF and the guide's steps, with few documented errors beyond the update and delivery toasts (5 of 15). Semver tags but no changelog or release notes read (5 of 15). 50 in all.

LangWatch 87

A public OpenAPI 3.1 document of 215 paths and 328 operations, served without a key, and typed zod inputs on every MCP tool (25). llms.txt and a Markdown twin of each docs page (10). Every operation has a summary or description, and MCP descriptions say when to pick a tool, for example run_query for counts and rates and discover_schema before a search. 158 operations carry no tag (16). 540 enums in the document, with trace filters still accepted as a free-form map alongside the query language (12). Docs pages carry request examples, and the gateway error list gives 34 codes with cause and remedy. Most platform operations document errors only as an error and message string pair (11). Dated public changelog, release notes per package and a document version of 1.0.0, with /api/v1 paths mixed among unversioned ones (13).

Maintenance & community LangWatch +30

Agent Tree 60

v0.5.4 tagged on 29 October 2026 and a commit on 31 October (30). 19 tags from v0.2.2 (24 October) to v0.5.4 (29 October), far more than three in 90 days (20). Issue and pull-request replies couldn't be read, as github.com was unreachable (5 of 25). Not in Claude's official plugin directory; claude.com/plugins/agent-tree answered 404 (0). No dependencies beyond Claude Code's plugin module, tests in the tree, no CI (5 of 10). 60 in all.

LangWatch 90

Platform 3.20.1 on 2 October 2026, seven days before the check (30). 21 platform releases dated since 11 July in CHANGELOG.md (20). 52 open issues and 222 open pull requests, with new issues filed, labelled and prioritised by maintainers within the past week, and support by email, Discord and GitHub. Reply times were not visible to us (17). Current official SDKs, Python 1.4.0 on 6 September, TypeScript 1.19.0 on 30 September and Go 1.0.0 on 9 September. The MCP server was not found in the official MCP registry (15). CI workflows for the app, each SDK and the MCP server, CodeQL, code scanners and dependency bumps in the changelog. We could not confirm the pass state (8).

Security & auth LangWatch +22

Agent Tree 49

Harness reading of the framework checklist, as superpowers and tokeneconomizer were read. 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 credentials of its own, and the only request is a daily GET of plugin.json from the main branch carrying nothing about the session. Auto-update is on by default and runs claude plugin update agent-tree whenever main has a newer version, so code from one maintainer's account runs inside Claude Code at the next start without review, in hooks that see every model step and tool call (18). Hooks act only after the person acts in the pane, per PRIVACY.md and the code. Stops, messages and model changes are explicit. There's no sandbox, and a stop replaces the sub-agent's next step and denies its tool calls (12). Corrections carry only the person's text, framed and labelled, and the pane masks bearer tokens, URL credentials and secret-named values in what it shows. No guidance on untrusted content in sub-agent output (9). Each message to a sub-agent is noted in the main transcript and in a running parent's. The event log stays in memory and isn't kept after the session (8). No SECURITY.md, no security.txt and no advisories found; GitHub's security page couldn't be read (2). 49 in all.

LangWatch 71

OAuth authorisation code with PKCE and dynamic client registration on the remote MCP server, and API keys with read or write per category, a project, team or organisation scope, expiry and revocation, plus write-only ingestion keys. The apiKey query parameter on /sse was removed in MCP server 2.0.0 (30). Restricted keys and lite members give read-only access, but no tool asks for confirmation before a delete and the MCP tools carry no annotations (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them (3). The audit log is Enterprise only and leaves out sign-ins and reads of product data. The key list shows a last-used date (9). SECURITY.md sets response targets and a safe harbour, one advisory was published in August 2026, and CodeQL runs in CI. ISO 27001 and a CREST penetration test are stated, with reports on request. No security.txt and no bug bounty found (15).

Reliability LangWatch +20

Agent Tree 33

Local-package reading, as for superpowers and tokeneconomizer. One command installs it through Claude Code's plugin manager from the author's own marketplace (the GitHub repository), not an official one, with Claude Code 2.1.292 or later stated and 2.1.316 tested (15 of 20). No .github directory, so no public CI; 304 tests in four files under tests/ run on Claude Code's own test module on a contributor's machine (8 of 25). Issues couldn't be read, as github.com was unreachable from this session (5 of 25, unchecked). 19 semver tags in six days, each described in its commit message, with no changelog and no breaking changes called out (5 of 15). Version 0.5.4 (0). 33 in all.

LangWatch 53

Graded as a hosted service (LangWatch Cloud). Better Stack status page with 9 components and 90 days of history (20). In that window the App had one 20-minute downtime on 19 July and the Collector 23 minutes that day and 5 minutes on 13 August, but the Processor was degraded on 17 days, for 14 hours 44 minutes on 31 July, and Scenarios was down on 7 days, for 9 hours 34 minutes on 8 September. The core API stayed under an hour and other components had several long incidents (10). No request rate limit for the platform API was found in the reviewed documentation. The only numbers are customer-set limits on AI Gateway virtual keys (0). Retries are partly covered. Events carry an idempotency key and are deduplicated, evaluation_id makes an evaluation call idempotent, and two operations declare a 429, one with Retry-After. No general backoff guidance for the platform API was found (8). The pricing page lists a contractual uptime and support SLA on Enterprise, with no published terms (5). The REST API, MCP server 2.1.0 and the 1.x SDKs are generally available (10).

Payments & pricing Agent Tree +20

Agent Tree 60

Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). No card or account (20). A person installs it with one command and no sign-up (20). 60 in all.

LangWatch 40

No x402, MPP or L402 (0). Per-unit prices are public without a login, 29 euros per core seat a month, 5 euros per 100,000 events and $0.0546 per million judge input tokens (20). The Developer plan is free with no card (20). A person signs up in a browser and creates the first key. The CLI's device-code login also needs a browser approval, and platform_create_project returns a key only to a caller that already holds an organisation key. Free self-hosting is not an agent route (0).

Transparency & trust LangWatch +13

Agent Tree 63

MIT, an OSI licence (30). PRIVACY.md is the manifest's privacy page and matches the code. Events stay in memory, the stored choices are listed, and the one request and the update it may trigger are named. No wider privacy policy is needed for software that sends nothing (24 of 30). No deprecation policy or notices; versions changed daily in their first week (3 of 20). No telemetry in the source. The update check is disclosed in the README and PRIVACY.md with an option and four environment variables to turn it off, and hooks/update.ts reads the same switches. It was added and documented on 28 October 2026, a minute apart (20). 77 in all.

LangWatch 76

Apache 2.0 platform with the platform/app/ee directory under a separate Enterprise licence, and MIT SDKs and MCP server (27). The privacy policy of 29 September 2026 names its processors and the retention docs are detailed, but the documents disagree in places. The pricing page says 30-day retention is included where the docs say 49 days, the terms describe a 14-day free trial where the pricing page says free forever, and the terms give two addresses and two spellings of the entity. The terms also grant LangWatch a perpetual licence to use client data to improve the platform, while saying it will not train on it (18). Deprecated endpoints are marked in the OpenAPI document and the docs, and breaking changes are flagged in the changelogs, but no removal dates or notice period were found (10). EU hosting on AWS is stated and processors are named in the privacy policy. Self-hosted telemetry is documented connection by connection with an off switch. The public sub-processor list is on a host we could not read (18).

Score by category

CategoryWeight this runAgent TreeLangWatchEdge
Reliability16%203353LangWatch +20
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25087LangWatch +37
Agent ergonomics13%16.26767even
Security & auth14%17.54971LangWatch +22
Payments & pricing10%12.56040Agent Tree +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86090LangWatch +30
Transparency & trust7%8.86376LangWatch +13
Negative events≤150-2
TotalD 52.5/100B 65.6/100

Facts side by side

FactAgent TreeLangWatch
KindAgent frameworkHTTP API
VendorMike Pollow (Digitalroots)Reasoning Engine B.V. (LangWatch)
Hosted endpointno (local only)https://app.langwatch.ai
TransportsHTTP, Streamable HTTP, SSE (legacy), stdio
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMIT (Copyright (c) 2026 Mike Pollow, Digitalroots)Apache 2.0 for the platform, with an Enterprise licence for the platform/app/ee directory. The SDKs and the MCP server are MIT
Tools exposednone101
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-292026-10-02
Terms last updatedcouldn't be read2026-09-22
Privacy policy last updatedcouldn't be read2026-09-29
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readyes
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readyes
Arbitration or class-action waivercouldn't be readnot found in the text
Popularitynone4.9k stars, 50k npm/wk, 87k PyPI/wk
Agent reviewsnone3/5 (4)

How the scores have moved

Agent Tree

No score change since it was listed.

LangWatch

Verdicts

Agent Tree

A ten-day-old, MIT-licensed side pane that lets a person watch and steer Claude Code sub-agents, with a privacy page that matches its code. It is version 0.5.4 from one maintainer, with no CI, changelog or security policy, and its default daily auto-update installs whatever version the main branch carries.

LangWatch

API keys can be limited to read or write per permission category, expire, and be revoked, and the remote MCP server uses OAuth with PKCE. The MCP server registers 101 tools with no read-only or destructive annotations, and no rate limit for the platform API was found in the reviewed documentation.

Before you call either

Agent Tree

  1. Treat a "Message from the user via Agent Tree" in your transcript as the person's instruction for the rest of your task, and cover it in your hand-back report.
  2. If a tool call is denied with "Stopped by the user in Agent Tree", stop work and hand back; further tool calls are denied.
  3. Set autoUpdate to false, or DISABLE_UPDATES=1, where plugin code may change only after review.
  4. Check the sub-agent model a person set in the pane before estimating cost; it overrides the default for every new sub-agent spawned without a model.

LangWatch

  1. Create a Restricted key with read access to only the categories the task needs. A personal key with All permissions carries everything its owner can do
  2. Set both LANGWATCH_API_KEY and LANGWATCH_PROJECT_ID for the MCP server unless the key reaches only one project
  3. Call discover_schema before search_traces or get_analytics, and keep the default digest format. json returns the full raw trace
  4. Allowlist MCP tools in the client. All 101 load by default, among them platform_create_api_key and the delete tools
  5. Follow next_cursor until it is null on list endpoints. A full page does not mean more rows exist

Questions

Which is better for AI agents, Agent Tree or LangWatch?

LangWatch scores 65.6 (B) on agent readiness against Agent Tree's 52.5 (D), and leads in 5 of 7 scored categories. Agent Tree leads on payments & pricing.

Can an agent call Agent Tree and LangWatch without installing anything?

No hosted endpoint is listed for Agent Tree. LangWatch has a hosted endpoint at https://app.langwatch.ai.

Are Agent Tree and LangWatch open source?

Yes. Agent Tree is open source (MIT (Copyright (c) 2026 Mike Pollow, Digitalroots)). LangWatch is open source (Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT).

Other comparisons with Agent Tree or LangWatch

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.