Skip to content
ProductArena

Rank #5 of 6 in AI Memory Layers

Cognee logo

Cognee

Open Source

Topoteretes UG

cognee.ai ↗Try it →
PA Score29/100AGENT-READY44/100BUILT-IN AI29/100API5/100
MCP✓CLI✓API✓
★ 30.7k▲ 10k/yrpypi 18.8k/wk★ +195pypi/wk -5.5k
ArenasAI Memory Layers#5/6

Access

Open app ↗API docs ↗CLI docs ↗MCP docs ↗

Install

pippip install cognee
cliuvx --from cognee cognee-cli demo

Compare head-to-head

Mem0 logovs Mem0Zep logovs ZepLetta logovs LettaSupermemory logovs SupermemoryAirweave logovs Airweave

Alternatives to Cognee →

Showcase

Cognee homepage screenshot
homepage · captured Sep 2026 · view live ↗
Cognee docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with Cognee before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$uvx --from cognee cognee-cli demo && uvx --from cognee cognee-cli forget --dataset demorecorded session — replayed, not live
recorded 2026-09-05 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

Claude logoClaudeAI AssistantsCline logoClineAI Coding AgentsCursor logoCursorAI Coding AgentsGitHub logoGitHubCode HostingLinear logoLinearProject ManagementNotion logoNotionProject ManagementSlack logoSlackTeam Chat

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

32.7/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

10.3/100

Data lifecycle — stories about data lifecycle in this arenaData lifecycleevidence →

Stories about data lifecycle in this arena

26.7/100

Deployment self host — stories about deployment self host in this arenaDeployment self hostevidence →

Stories about deployment self host in this arena

70.5/100

Graph entity memory — stories about graph entity memory in this arenaGraph entity memoryevidence →

Stories about graph entity memory in this arena

46.0/100

Memory recall quality — stories about memory recall quality in this arenaMemory recall qualityevidence →

Stories about memory recall quality in this arena

48.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

46.2/100

Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plansevidence →

Plan structure and value — what each tier costs and what it unlocks

24.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

35.8/100

Retrieval performance — stories about retrieval performance in this arenaRetrieval performanceevidence →

Stories about retrieval performance in this arena

0.0/100

Sdk integrations — stories about sdk integrations in this arenaSdk integrationsevidence →

Stories about sdk integrations in this arena

17.1/100

Session context — stories about session context in this arenaSession contextevidence →

Stories about session context in this arena

47.8/100

Tenancy permissions — stories about tenancy permissions in this arenaTenancy permissionsevidence →

Stories about tenancy permissions in this arena

38.0/100

Story verdicts — every judged story with its evidenceStory verdicts

What’s free: 34 free · 0 paid · 0 enterprise · 2 not stated in evidence

?

Sorted by importance (agentic first) (high → low) · 57/57 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3fullfree8/10T

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3fullfree7/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2fullfree8/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2fullfree7/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partialfree6/10T

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partialfree6/10C

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partialfree6/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1partialfree6/10C

Add memories from conversations and retrieve them later with semantic search, so context persists across sessions C

Core memory

developerMemory recall quality — stories about memory recall quality in this arenaMemory recall quality3fullfree8/10X

My agent can manage its own memory mid-conversation — adding, searching, updating, and deleting memories through tools or API calls it invokes itself C

Agent memory

ai-native userMemory recall quality — stories about memory recall quality in this arenaMemory recall quality3fullfree8/10T

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3fullfree8/10X

Self-host the memory layer from open-source code (e.g. via Docker) on infrastructure I control C

Self host

platform-engineerDeployment self host — stories about deployment self host in this arenaDeployment self host3fullfree8/10C

Store memories as a knowledge graph of entities and relationships so multi-hop and entity-centric questions are answerable C

Knowledge graph

ml-engineerGraph entity memory — stories about graph entity memory in this arenaGraph entity memory3fullfree8/10X

Get summaries of past sessions or threads so an agent can pick up where the last conversation left off C

Context assembly

developerSession context — stories about session context in this arenaSession context3partialfree7/10C

Scope memories per user, agent, or application so one tenant's memories never leak into another's retrieval C

Isolation

developerTenancy permissions — stories about tenancy permissions in this arenaTenancy permissions3partialfree7/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partialfree5/10C

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3partialfree5/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2fullfree8/10C

Delete a user's memories on demand — single memory, per-entity, or full erasure — to satisfy privacy requirements C

Forgetting

platform-engineerData lifecycle — stories about data lifecycle in this arenaData lifecycle2fullfree8/10C

Ingest documents, JSON, and business data into memory — not just chat transcripts C

Ingestion

developerSession context — stories about session context in this arenaSession context2fullfree8/10C

Connect off-the-shelf assistants (Claude, ChatGPT, Cursor) to the same memory so every tool I use shares what it knows about me C

Agent memory

ai-native userSdk integrations — stories about sdk integrations in this arenaSdk integrations2partialfree7/10T

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partialfree6/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partialfree6/10T

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partialfree6/10C

The memory layer decides for itself what is worth remembering — extracting salient facts from raw conversation and consolidating them in the background C

Agent memory

ai-native userMemory recall quality — stories about memory recall quality in this arenaMemory recall quality2partialfree6/10C

Govern who and what can read or write memory with roles, policies, or access-control lists, and audit that access C

Governance

platform-engineerTenancy permissions — stories about tenancy permissions in this arenaTenancy permissions2partialfree5/10C

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partialfree5/10C

Rely on the memory layer to update, supersede, or merge memories when new information contradicts what was stored C

Core memory

developerMemory recall quality — stories about memory recall quality in this arenaMemory recall quality2partialfree5/10C

Retrieve a token-budgeted, prompt-ready context block assembled from relevant memories in one call C

Context assembly

developerSession context — stories about session context in this arenaSession context2partialfree5/10C

Steer retrieval with metadata filters, keyword/hybrid search modes, or reranking instead of accepting a single fixed similarity search C

Retrieval controls

developerMemory recall quality — stories about memory recall quality in this arenaMemory recall quality2partialfree5/10C

See published pricing with a free tier and per-unit rates so I can project memory costs before committing G

Pricing

platform-engineerPricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans2partial4/10C

Build against official SDKs in at least Python and TypeScript with equivalent memory APIs C

Sdks

developerSdk integrations — stories about sdk integrations in this arenaSdk integrations2partial3/10T

Drop the memory layer into agent frameworks like LangChain, LangGraph, CrewAI, or the Vercel AI SDK via documented first-party integrations C

Frameworks

developerSdk integrations — stories about sdk integrations in this arenaSdk integrations2none0/10

Export memories in a machine-readable format so the memory store is portable and not a lock-in trap C

Portability

platform-engineerData lifecycle — stories about data lifecycle in this arenaData lifecycle2none0/10

Ingest at scale with async or batch processing and check the status of background memory operations C

Scale

platform-engineerRetrieval performance — stories about retrieval performance in this arenaRetrieval performance2none0/10

Make memories expire or decay — via TTL, expiration dates, or recency weighting — so stale facts stop surfacing C

Forgetting

developerData lifecycle — stories about data lifecycle in this arenaData lifecycle2none0/10

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

See documented retrieval-latency targets or measured numbers (e.g. p50/p95) backing the product's speed claims C

Latency

platform-engineerRetrieval performance — stories about retrieval performance in this arenaRetrieval performance2noneuntestednone yet

See published memory-quality benchmark results (e.g. LongMemEval, LoCoMo) backing the product's recall-accuracy claims C

Benchmarks

ml-engineerMemory recall quality — stories about memory recall quality in this arenaMemory recall quality2noneuntestednone yet

Track when facts became valid or invalid (temporal reasoning) so the memory distinguishes current from outdated information C

Knowledge graph

ml-engineerGraph entity memory — stories about graph entity memory in this arenaGraph entity memory2noneuntestednone yet

Run the memory layer fully locally — embedded in-process or against local models — without any cloud dependency C

Self host

developerDeployment self host — stories about deployment self host in this arenaDeployment self host1partialfree7/10C

Share selected memory across multiple agents or users (team or group memory) while keeping private memory private C

Sharing

developerTenancy permissions — stories about tenancy permissions in this arenaTenancy permissions1partialfree7/10C

Customize the memory schema — entity types, edge types, or ontology — to match my domain C

Schema customization

ml-engineerGraph entity memory — stories about graph entity memory in this arenaGraph entity memory1partialfree6/10X

Store images, PDFs, or other files as memory inputs and recall information from them later C

Ingestion

developerSession context — stories about session context in this arenaSession context1partialfree6/10C

Wire memory into real-time voice pipelines (e.g. LiveKit, Pipecat, ElevenLabs) with documented integrations fast enough for live conversation C

Frameworks

developerSdk integrations — stories about sdk integrations in this arenaSdk integrations1none0/10

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1n/auntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 43 stories with headroom

What would move Cognee’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product

    nonemoves Built-in AIimpact 45

    Cognee positions itself as a memory/knowledge-graph backend that other AI assistants (Claude, Cursor, Cline) connect to via MCP, not as a product with its own built-in assistant that users delegate tasks to.

  2. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    Evidence only shows Cognee shipping its own MCP server so external AI tools (Claude, Cursor, Cline) can call Cognee's memory tools — the reverse direction of the story.

  3. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    nonemoves PA Scoreimpact 30

    Cognee's evidence pack shows manual operations (remember, recall, improve, forget) invoked via API, CLI, or MCP calls, but no evidence of a rules/trigger engine that fires actions automatically on events (e.g., webhooks, event listeners, conditional automations).

  4. Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent

    nonemoves agent-readyimpact 30

    Missing: aPI key/credential issuance mechanism, scoping/least-privilege token model, documentation of credential lifecycle management.

  5. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    No evidence anywhere in the pack mentions webhooks, event subscriptions, or push notifications; Cognee's integrations (Slack, GitHub, Linear) are described as data sources to ingest, not as an event/webhook subscription mechanism for users.

  6. Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples

    nonemoves API qualityimpact 30

    Missing: any interactive/runnable API explorer (e.g., Swagger UI, Postman collection, live code sandbox) and independent confirmation of one working.

  7. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    Cognee has an 'api-reference' section referencing a REST API and Docker deployment, but a direct probe for OpenAPI/Swagger specs at all standard locations (openapi.json, swagger.json, etc.) returned 404s, and no documentation page links to a downloadable machine-readable spec.

  8. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    Missing: any versioning scheme documentation, explicit deprecation policy, changelog/migration guides for breaking changes.

Showing the top 8 of 43 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map13 surfaces · 38 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

Core concepts docs25 stories

Cognee CLI docs13 stories

Pricing docs10 stories

API reference8 stories

Cognee cloud docs8 stories

Getting started docs6 stories

Python API docs6 stories

Cognee MCP docs5 stories

Hacker News4 stories

OpenAPI spec3 stories

Llms integrations docs3 stories

cognee.ai2 stories

llms.txt1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$uvx --from cognee cognee-cli demo && uvx --from cognee cognee-cli forget --dataset demoreproduced
$ uvx --from cognee cognee-cli demo && uvx --from cognee cognee-cli forget --dataset demo
Loading the bundled demo knowledge graph (no API [redacted] required)...
Success: Demo graph loaded into dataset 'demo' (47 nodes, 86 edges).

Query: Who works at Anthropic?
  1. Recall queries can traverse this graph: "who works at Anthropic" returns Alice, "what does Cognee depend on" returns litellm and Ladybug,
  2. the results in a graph database plus a vector store. For example, Alice works at Anthropic in San Francisco. She contributes to the Cognee project.
  3. Cognee is an open-source AI memory platform. It transforms raw text, files, and URLs into a persistent knowledge graph that agents can query.

Query: What does cognee depend on?
  1. Recall queries can traverse this graph: "who works at Anthropic" returns Alice, "what does Cognee depend on" returns litellm and Ladybug,
  2. The Cognee project depends on litellm for LLM routing and on Ladybug as its default graph backend.
  3. the results in a graph database plus a vector store. For example, Alice works at Anthropic in San Francisco. She contributes to the Cognee project.

This demo uses [redacted]word search (CHUNKS_LEXICAL) — it needs no LLM and no embeddings. LLM answers over your own data need LLM_API_[redacted] set.
Next: cognee-cli search "your question" -t CHUNKS_LEXICAL -d demo
Then: set LLM_API_[redacted] and run cognee-cli remember "<path-or-text>" to build memory from your own data.
Clean up with: cognee-cli forget --dataset demo
Success: Done: {'dataset_id': '2c17f96f-27cf-56e7-a036-5592dcc8b4fd', 'status': 'success'}
Next: cognee-cli remember <path-or-text> -d demo to start a new session.
proves: Use an official CLIproves: Run the memory layer fully locally — embedded in-process or against local models — without any cloud dependencyrecorded 2026-09-05
$echo '<jsonrpc initialize>' | uvx cognee-mcpreproduced
$ echo '<jsonrpc initialize>' | uvx cognee-mcp
⠋ Resolving dependencies...                                                     
⠙ Resolving dependencies...                                                     
⠋ Resolving dependencies...                                                     
⠙ Resolving dependencies...                                                     
⠙ cognee-mcp==0.5.5                                                             
⠙ cognee==1.5.4                                                                 
⠙ cognee==1.5.4                                                                 
⠙ ladybug==0.19.0                                                               
⠙ ladybug==0.19.0                                                               
⠙ cognee==1.5.4                                                                 
⠙ cognee==1.5.4                                                                 
⠙ httpx==0.28.1                                                                 
⠙ mcp==1.29.1                                                                   
⠙ uv==0.12.10                                                                   
⠙ aiofiles==25.1.0                                                              
⠙ aiohttp==3.14.3                                                               
⠙ aiolimiter==1.2.1                                                             
⠙ aiosqlite==0.22.1                                                             
⠙ alembic==1.19.2                                                               
⠙ cbor2==6.1.4                                                                  
⠙ cryptography==50.0.1                                                          
⠙ datamodel-code-generator==0.76.2                                              

2026-09-05T00:47:02.614301 [info     ] Log file created at: /Users/judegomila/.cognee/logs/2026-09-04_17-47-02.log [cognee.shared.logging_utils] log_file=/Users/judegomila/.cognee/logs/2026-09-04_17-47-02.log

2026-09-05T00:47:02.614462 [warning  ] Cognee 1.0 changes: New API — remember/recall/forget/improve (V1 add/cognify/search still work). Session memory enabled by default (CACHING=false to disable). Multi-user access control on by default (ENABLE_BACKEND_ACCESS_CONTROL=false to disable). Agents (@cognee.agent) auto-verified on registration. See https://docs.cognee.ai/ [cognee.shared.logging_utils]

2026-09-05T00:47:02.614531 [info     ] Logging initialized            [cognee.shared.logging_utils] cognee_version=1.5.4 database_path=/Users/judegomila/.cache/uv/archive-v0/Zc-zBsYgUxmmVznI/lib/python3.13/site-packages/cognee/.cognee_system/databases os_info='Darwin 25.5.0 (Darwin Kernel Version 25.5.0: Tue Jun  9 22:28:34 PDT 2026; root:xnu-12377.121.10~1/RELEASE_ARM64_T6050)' python_version=3.13.15 structlog_version=25.5.0

2026-09-05T00:47:02.614585 [info     ] Database storage: /Users/judegomila/.cache/uv/archive-v0/Zc-zBsYgUxmmVznI/lib/python3.13/site-packages/cognee/.cognee_system/databases [cognee.shared.logging_utils]

2026-09-05T00:47:02.770852 [info     ] auth posture: authentication=required, multi_tenant=enabled (default (no env vars set)) [get_authenticated_user]

2026-09-05T00:47:04.314340 [info     ] Cognee client initialized in direct mode [cognee.shared.logging_utils]

2026-09-05T00:47:04.314474 [info     ] MCP transport security: using SDK defaults (localhost only) [cognee.shared.logging_utils]

2026-09-05T00:47:04.314520 [info     ] Running database migrations... [cognee.shared.logging_utils]

setup plugin alembic.autogenerate.schemas

setup plugin alembic.autogenerate.tables

setup plugin alembic.autogenerate.types

setup plugin alembic.autogenerate.constraints

setup plugin alembic.autogenerate.defaults

setup plugin alembic.autogenerate.comments

setup plugin alembic.ext.checkconstraint_byname

Using database: sqlite+aiosqlite:////Users/judegomila/.cache/uv/archive-v0/Zc-zBsYgUxmmVznI/lib/python3.13/site-packages/cognee/.cognee_system/databases/cognee_db

Context impl SQLiteImpl.      

Will assume non-transactional DDL.

Relational migrations applied (target head).

2026-09-05T00:47:04.484187 [info     ] Database migrations done.      [cognee.shared.logging_utils]

2026-09-05T00:47:04.484315 [info     ] Running MCP server with stdio  [cognee.shared.logging_utils]
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2025-06-18","capabilities":{"experimental":{},"prompts":{"listChanged":false},"resources":{"subscribe":false,"listChanged":false},"tools":{"listChanged":false}},"serverInfo":{"name":"Cognee","version":"1.29.1"}}}
proves: Connect an agent via an official MCP serverrecorded 2026-09-05

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 15 testable claims verified · 0 contradicted → integrity 33/100

20 distinct capability claims found in Cognee’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

10

Unverified

0

Contradicted

23

Undersold

Verified (6)
Unverified (14)
Undersold (23)
Claims outside our story set (3)

Real capability claims found in Cognee’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “cognee-cli push uploads a local dataset's knowledge graph to Cognee Cloud”

    source ↗

  • “The browser UI lets you upload data, explore knowledge graphs, run searches, and manage datasets”

    source ↗

  • “Cognee can index code repositories into memory”

    source ↗
Suggest a story for these →

Business model

open-sourcefree-tierusage-basedenterprise-custom

Apache-2.0 open-source core you can run anywhere; Cognee Cloud offers a free developer tier then usage-priced managed plans and custom enterprise deployments.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score40 (Sep 5 '26)29 (Sep 16 '26)
Agent-ready59 (Sep 5 '26)44 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Agent surface uptime llms.txt 100% (30d, checked every 6h since Sep 8 '26)