Cognee is an AI memory platform that stores information in a self-hosted knowledge graph so agents can retain context across sessions. It ingests data, connects related information, and helps agents retrieve it for reasoning and actions. The catalogue includes skills and instructions that extend agent workflows around Cognee.
Borrowing it
Nothing to install: this file belongs to topoteretes/cognee. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/topoteretes/cognee/main/.agents/skills/cognee-performance/SKILL.mdgit clone --depth 1 https://github.com/topoteretes/cogneeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/topoteretes/cognee/cognee-performance)<a href="https://agentmods.dev/skills/topoteretes/cognee/cognee-performance"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-performance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/topoteretes/cognee/cognee-performance"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.02609 |
| Opus 5.5 | $0.00028 | $0.01044 |
| Sonnet 5.5 | $0.00014 | $0.00522 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
cognee-performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tune cognee's performance
The LLM is the bottleneck. Building the graph costs two LLM calls per chunk (graph extraction and summarization), and almost every other tuning question comes down to how many of those calls run, how fast, and on which model. Database and embedding work is small next to that.
Use it
1. Estimate before you ingest
estimate = await cognee.remember("./docs", dry_run=True)
print(estimate) # per-stage token counts and approximate cost; no LLM calls
The estimate covers graph extraction and summarization only, not
improve() or embeddings. Not available with
GLiNER or a remote instance.
2. Ingestion knobs
All are remember() arguments (and cognify() ones):
| Knob | Default | What it controls |
|---|---|---|
data_per_batch |
20 | How many documents are processed at the same time (a concurrency limit, not a batch). Lower it to reduce load; raise it for many small files. |
chunks_per_batch |
2000 (env CHUNKS_PER_BATCH) |
How many chunks each extraction/storage call receives. Lower it to spread load and fail smaller. The DLT pipeline defaults to 100. |
chunk_size |
min(embedding max tokens, LLM max tokens / 2); about 8191 tokens with default OpenAI models | Max tokens per chunk. Fewer, bigger chunks mean fewer LLM calls; smaller chunks mean finer-grained graphs. |
run_in_background |
False |
Return immediately (status="running"); await result later. |
self_improvement |
True |
improve() after the graph is built. False (or IMPROVE_AUTO_ENABLED=false) skips that extra work. |
Worst-case concurrent LLM calls are about
data_per_batch × min(chunks per document, chunks_per_batch) × 2, and there
is no separate concurrency cap. The rate limiter below is the brake.
Several datasets in one cognify(datasets=[...]) call run one after
another, not in parallel.
3. LLM throttling and models
| Env var | Default | Notes |
|---|---|---|
LLM_RATE_LIMIT_ENABLED |
false |
Turn on a requests-per-interval limit |
LLM_RATE_LIMIT_REQUESTS / LLM_RATE_LIMIT_INTERVAL |
60 / 60 s | 10 requests for local providers (Ollama, llama.cpp, LM Studio) |
AUTO_RATE_LIMIT |
true |
On a 429/503/529 or timeout, switches the limiter on for 15 minutes (extended while errors continue) |
LLM_EXTRACTION_MODEL / _PROVIDER / _ENDPOINT / _API_KEY / _API_VERSION |
the main model | Use a cheaper or faster model just for graph extraction |
LLM_SUMMARIZATION_*, LLM_QUERY_* |
the main model | Same, for summaries and for answering queries |
LLM_MAX_COMPLETION_TOKENS |
16384 | Also caps the default chunk size (half of it) |
LLM_ARGS |
— | Extra litellm arguments merged into every call, e.g. a request timeout |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed 463891ca174b
- 1mo ago Changed 298b930d1191
- 1mo ago First seen · 187 lines · 70 tokens per session scan A 382f23bb74af
cognee-performance is a skill published in the GitHub repository topoteretes/cognee (33,094 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 2,609 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
cognee-performance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cognee-performancetopoteretes/cognee | Skill | 33k | today | Apache-2.0 | A | 70 | Claude Code, Codex |
| openmemoryCaviraOSS/OpenMemory | Skill | 4.6k | 19d ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| memseek-remembermemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 24 | Claude Code |
| memseek-explainmemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 25 | Claude Code |
| memseek-searchmemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 22 | Claude Code |
| surface-learningsterrizoaguimor/celiums-memory | Skill | 23 | 2mo ago | Apache-2.0 | A | 60 | Claude Code |
| context-recoveryterrizoaguimor/celiums-memory | Skill | 23 | 2mo ago | Apache-2.0 | A | 37 | Claude Code |