At a glance
- Category
- Agent tools and integrations
- Tags
- Freemium, Self-hosted
Company
- Founded
- 2024
Code
- Last push
- 15 October 2026
For developers
- SDKs
- Python, TypeScript
- Runs
- Cloud, Self-hosted
- Works with
- Claude Code, Codex, OpenClaw, Snowflake, Postgres, Slack and 16 more
Cognee in our research
All researchStudy
AI Tool Pricing Index, November 2026
Pricing
Usage-based
43 of the 361 tools we checked bill by usage.
Edition price, checked 5 November 2026.
Pricing pages of the AI tools, November 2026 editionas of n = 361 tools checked
What is Cognee?
Cognee is a memory layer for AI agents that ingests warehouses, vector stores, files, and APIs, then parses and organizes them into a managed world model for reusable context. Its Ingest, Reason, and Act flow includes Ontology, Managed store, and Permissions control, and it integrates with Claude Code, Cursor, LangGraph, and CrewAI. Plans run Free, Developer $35/month, Cloud (Team) $200/month, and On-Prem (Enterprise) custom.
What it actually does
Cognee ingests unstructured data (documents, chat history, code) and builds a knowledge graph plus vector index that AI agents can query for context across sessions. The pitch against plain RAG is that chunk-based vector search loses the relationships between facts, so multi-hop questions ("which of these three vendors reported an incident, and when") fail; a graph structure preserves those links. It ships as a self-hosted Python library/pipeline (github.com/topoteretes/cognee) and as a hosted "Cognee Cloud" service with the same core engine.
Where it's positioned vs. Mem0 and similar tools
The clearest way to place Cognee is against Mem0, the other widely-used agent-memory library. Mem0 is built for single-agent, single-user memory (personalizing one user's chat history) and gates its knowledge-graph feature behind a paid tier. Cognee is built for multi-agent memory — several agents reading and writing the same graph — and includes graph capability in the free/open-source tier from the start. Third-party technical writeups (e.g. a comparison at vectorize.io) generally agree with this framing: graph-based recall wins on multi-hop correctness, vector-only recall wins on raw simplicity and latency for single-fact lookups. Benchmark numbers Cognee cites for itself (e.g. its BEAM-benchmark results) come from its own blog, not an independent source, and should be read as a vendor claim.
Development activity and licensing
The core repo is Apache-2.0 with a single, unambiguous LICENSE file (no split code/docs licensing). It's substantially active, with pushes to main day to day and frequent PyPI releases (v1.5.0 among them). Releases are frequent — four tagged releases in the two weeks before this check, including active dev-preview tags — which is a healthy sign for a tool you'd depend on in production, not a healthy sign in itself of code quality.
How pricing works
Self-hosting the open-source engine is free indefinitely — you run it on your own infrastructure and pay only for whatever LLM/vector-store calls it makes. The managed Cognee Cloud has three tiers, all with real numbers published (not "contact us" placeholders): Free ($0/month, 1M tokens included, 1 workspace, unlimited users and API calls), Standard ($2.50 per 1M tokens processed, plus $5 per additional workspace, adds Slack/Notion/Google Drive source integrations and in-app support), and Enterprise (custom pricing, adds a dedicated support engineer, bring-your-own-cloud, and SLAs). At meaningful token volume the Standard tier's usage-based pricing is the number to model against your expected ingestion volume, not the flat access-fee model most SaaS tools use.
Company, funding, and data handling
Cognee is built by a Berlin-based team (legal entity trades as topoteretes/Cognee) that raised a $7.5M seed round led by Pebblebed, with 42CAP and Vermilion Ventures participating, announced February 2026 and reported independently by EU-Startups and Pulse2 in addition to the company's own post. The vendor's /trust page states GDPR-aligned processes maintained via a third party (heyData), a DPA available on request, and three deployment options including fully local ("your data never leaves your infrastructure") — but it does not claim SOC 2 or any other formal security certification, and there's no separate named security/compliance audit page beyond that one trust page.
What's still thin
Cognee has zero reviews on G2 and none found on Trustpilot as of this check — it's simply too early for independent user review volume to exist yet, which is normal for a tool that hit 1.0 in June 2026, not a red flag on its own. The customer names the vendor lists (Bayer, University of Wyoming, Knowunity, SlideSpeak, Dynamo, DeepMetis) are vendor-published; the University of Wyoming one has a detailed named case study on Cognee's own blog, but none of the six were independently corroborated in this research. Treat vendor figures like "5M+ SDK runs/month" and "70+ companies running it live" the same way — plausible given the GitHub activity, but not independently verifiable.
Cognee price and terms
Terms
- Free plan
- YesYes
The terms in full
Free plan at $0/month, described as free forever: 1 workspace and 1M tokens included, no card required, with unlimited users and unlimited API calls. Processing beyond the included 1M tokens moves a buyer to the Standard usage rate of $1.00 per 1M tokens, and extra workspaces cost $5 each per month.
For AI agents
- MCP server
- YesChecked by us,

Pricing page, captured
cognee.ai/pricing, checked
All plans and limits
| Plan | Price | Main limits |
|---|---|---|
| Free | $0 a month | Workspaces: 1 workspace; Unlimited API calls; 1M tokens included |
| Enterprise | Price on request | None stated |
| Standard | $1 per 1M tokens | Unlimited workspaces — $5 each per month |
Read from cognee.ai/pricing.
What we checked on Cognee
What the price counts
Metered on usage: the Standard plan charges $1.00 per 1M tokens processed with no seat charge, and adds a fixed $5 per month for each workspace beyond the first. The Free plan covers 1M tokens in 1 workspace, and Enterprise is quote-only, sold as a fixed-scope BYOC engagement of 6, 12 or 24 months with no figure published.
Start free. Pay one flat rate for the tokens your memory processes, and add fixed costs only when you add workspaces.
cognee.ai/pricingChecked
MCP server
MCP server at mcp.aws.cognee.ai, behind OAuth sign-in
https://mcp.aws.cognee.ai/mcp
mcp.aws.cognee.ai/.well-known/oauth-pro…Checked by us,
Open source
Apache-2.0 licence in its public repository
Apache License Version 2.0
github.com/topoteretes/cognee/blob/main…Checked by us,
Questions about Cognee
- How much does Cognee cost?
- Cognee has a free plan. Its paid plans are Enterprise and Standard at $1 per 1M tokens. From cognee.ai/pricing, checked 5 November 2026.
- Does Cognee have an API or an MCP server?
- Cognee has an MCP server. We checked mcp.aws.cognee.ai/.well-known/oauth-protected-resource/mcp ourselves on 15 November 2026.
- Is Cognee open source, and can you host it yourself?
- Cognee is open source. We checked github.com/topoteretes/cognee/blob/main/LICENSE ourselves on 15 November 2026. You can host Cognee yourself.
- What have we checked on Cognee?
- 3 facts, under these headings: What it costs to start, how you build with it.
- How do we check Cognee?
- We hold 3 facts on Cognee, quoted from 4 pages. Facts last checked 15 November 2026. Price last checked 5 November 2026. Last change found 15 November 2026.
Sources and changes
Last full check
Sources on cognee.ai2
What changed1
- What it does
Repository
- Licence
- Apache-2.0
- Stars
- 32,363
- Last push
- 15 October 2026
Cognee price history
Cognee had a free plan, and paid plans from $1 per 1m tokens, on both of our reads, from 1 November 2026 to 5 November 2026.
| Price | Plan | First seen | Last seen | Readings | Source |
|---|---|---|---|---|---|
| $1 per 1m tokens | Cheapest paid plan | 1 November 2026 | 5 November 2026 | 2 | Pricing page, read 1 November 2026 |
From our research, read twice since 1 November 2026. 9 more of our checks could not pick this price out of the page and are left out. A date is when we read the page, not when the price changed.
Similar in Agent tools and integrations
See all in Agent tools and integrations
- ERIUS PHONERented cloud Android phones, each in its own container, that keep an agent's apps and sign-ins between sessions.
- TinyFishWeb search, page fetching, cloud browsers and goal-driven web automation for AI agents, with search and fetch free.
- SmitheryPublic MCP server registry, now run by Arcade, listing direct vendor MCP URLs after its proxy shut down.
- UI DiscoveryA library of real websites, iOS apps and dashboards with each one's palette, fonts and original build prompt.
Is Cognee yours?
Free, and the page then carries the verified owner mark. You confirm it with an email at cognee.ai. Claim this listing
Report an error if a fact is wrong.