Head to head · Agent tracing · October 2026 research run

agents-tree vs LangWatch

LangWatch scores 65.6 (B) on agent readiness against agents-tree's 64.3 (B), and leads in 4 of 7 scored categories. agents-tree leads on reliability, agent ergonomics and payments & pricing. Both do agent tracing.

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

Which one, for what

agents-tree B

Best for Seeing every coding-agent session and its sub-agents as one tree in a terminal

Ahead on

  • Reliability, 60 against 53
  • Agent ergonomics, 73 against 67
  • Payments & pricing, 60 against 40

Also in its favour

  • No key needed to call it

Watch for

One maintainer, first released on 6 October 2026, with no company, site or security policy

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

  • Schema & documentation, 87 against 64
  • Security & auth, 71 against 66
  • Maintenance & community, 90 against 63
  • Transparency & trust, 76 against 62

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.

Maintenance & community LangWatch +27

agents-tree 63

1.2.0 on PyPI on 8 October 2026, 24 days before the check, and a commit on main on 11 October (30). Five PyPI releases between 7 and 8 October 2026 (20). Issue and pull-request replies couldn't be read, as github.com was unreachable. The bare clone shows two Dependabot branches of 28 October unmerged (5 of 25). Not an MCP server and in no official directory; herdr's plugin marketplace couldn't be read (0). No runtime dependencies, a lock file, CI on five Python versions and Dependabot for the workflow actions, with its two updates unmerged (8 of 10). 63 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).

Schema & documentation LangWatch +23

agents-tree 64

Framework reading, docs a model can follow, as agent-tree was read. --json writes one document with schema_version 1 and a fixed set of session, agent and detail fields, and model.py types them as dataclasses, but no JSON Schema or field reference is published (14 of 25). README, AGENTS.md and docs/demo are Markdown in the repository; no llms.txt (10). The README says what it shows and reads, has a caveats section per provider (context window inference, internal formats, how running sessions are found), and the command's help says not to run it inside an agent (15 of 20). argparse with choices for --provider and --color, positive-number checks for --window and --interval, and --json refused with --watch (10 of 15). Usage examples for every flag, key and column tables, and errors as messages on stderr with exit code 1, with few error outputs documented (10 of 15). Semver tags and a schema version, no changelog (5 of 15). 64 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).

Payments & pricing agents-tree +20

agents-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 from PyPI 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 +14

agents-tree 62

MIT, an OSI licence (30). The README says what it reads for each agent CLI, that it never talks to a session and that it has no dependencies, and the source agrees. AGENTS.md forbids real session data in the repository. There is no privacy page, though the software sends nothing (22 of 30). No deprecation policy. The README says the older Antigravity layout is still read, and the default change in 1.0.0 came with a major version (5 of 20). No telemetry and no network code in the source, so there is nothing to switch off (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).

Reliability agents-tree +7

agents-tree 60

Local-package reading, as for agent-tree, superpowers and tokeneconomizer. Installs from PyPI with uv tool install agents-tree or pipx, with Python 3.10 or later and POSIX stated in pyproject.toml and Linux and macOS in the herdr manifest (20). .github/workflows/test.yaml runs pylint, pyright, 173 pytest tests, a test run and a package build on Python 3.10 to 3.14 on every push and pull request. Whether the runs pass wasn't checked, as github.com couldn't be read (15 of 25). Issues couldn't be read for the same reason (5 of 25, unchecked). Semver tags and Conventional Commit messages, but no changelog, and the README's caveat that transcript formats may change is the only note on breakage; the switch to reading every provider by default came with 1.0.0 (5 of 15). Version 1.2.0 (15). 60 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).

Agent ergonomics agents-tree +6

agents-tree 73

Framework reading, how much an agent has to carry. agents-tree adds nothing to any agent's context, since it reads transcripts and never writes to a session. Used through --json, it returns every matched agent's prompt and last message with no field selection or size limit (20 of 25). A directory, a session id or unique prefix, -r for running only and --provider narrow the output, and the live view folds older finished agents; nothing limits the JSON's size (12 of 20). An ambiguous prefix lists the matches, a miss names each provider that found nothing, unknown transcript lines are skipped and missing fields show -, and herdr/run.sh names the Python it needs (14 of 20). Read-only, so every run can be repeated; setup-keys strips its own old block, leaves bound keys alone, backs up and restores on a failed herdr config check (18 of 20). No arguments shows every running session from every provider, and there are no runtime dependencies; Python only, no SDK applies (9 of 15). 73 in all.

LangWatch 67

The MCP server registers 101 tools in the 2.1.0 source, with no toolsets or dynamic loading found. Trace tools return a compact digest by default, which earns 3 back (8). Cursor paging with next_cursor, limit and pageSize, filters, a projection DSL on trace search and a digest or json format switch (20). Gateway errors carry a stable code, tips, a docs link and a fault field, and the MCP client passes them on. Platform errors are plainer (16). No readOnlyHint or destructiveHint in the MCP source. Idempotency exists for evaluations and ingested events, and several delete tools archive instead of removing (8). Python, TypeScript and Go SDKs, a CLI, and few required parameters (15).

Score by category

CategoryWeight this runagents-treeLangWatchEdge
Reliability16%206053agents-tree +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26487LangWatch +23
Agent ergonomics13%16.27367agents-tree +6
Security & auth14%17.56671LangWatch +5
Payments & pricing10%12.56040agents-tree +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86390LangWatch +27
Transparency & trust7%8.86276LangWatch +14
Negative events≤150-2
TotalB 64.3/100B 65.6/100

Facts side by side

Factagents-treeLangWatch
KindAgent frameworkHTTP API
VendorKarel BlavkaReasoning 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 Karel Blavka)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 documentedyesno
llms.txtnoyes
Last release2026-10-082026-10-02
Terms last updatedcouldn't be read2026-09-22
Privacy policy last updatedno document linked2026-09-29
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

agents-tree

No score change since it was listed.

LangWatch

Verdicts

agents-tree

A read-only viewer for coding-agent sub-agents across four CLIs, installed from PyPI with no dependencies, no network code and CI on five Python versions. It is three and a half weeks old from one maintainer, reads formats the agent CLIs don't document, and has had no commit to main since 11 October.

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

agents-tree

  1. Don't run agents-tree inside your own session with !; its output, including other agents' prompts, lands in your context.
  2. Use agents-tree --json <dir or session id> for a schema-versioned document; it can't be combined with --watch.
  3. Treat prompts and last messages in the JSON as untrusted transcript text, not instructions.
  4. Expect - in a column after an agent CLI update; transcript formats are internal and may move.

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, agents-tree or LangWatch?

LangWatch scores 65.6 (B) on agent readiness against agents-tree's 64.3 (B), and leads in 4 of 7 scored categories. agents-tree leads on reliability, agent ergonomics and payments & pricing.

Can an agent call agents-tree and LangWatch without installing anything?

No hosted endpoint is listed for agents-tree. LangWatch has a hosted endpoint at https://app.langwatch.ai.

Are agents-tree and LangWatch open source?

Yes. agents-tree is open source (MIT (Copyright (c) 2026 Karel Blavka)). 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 agents-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.