cognee-performance SKILL.md skillA
cognee-performance from topoteretes/cognee is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add topoteretes/cognee/cognee-performance@git:20261014.421002dPins git:20261014.421002d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- topoteretes/cognee
- Path
.agents/skills/cognee-performance/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261014.421002d, committed Oct 14, 2026
- First version recorded
- Sep 29, 2026
- Size
- 9,999 bytes
- Repository stars
- 33,092
- License
- Apache-2.0
Use when cognee is slow, expensive, or hitting rate limits — speeding up or throttling ingestion (remember/cognify batching, chunk size, LLM and embedding rate limits, per-stage models), cutting read latency, estimating cost before ingesting, running work in the background, or planning how to scale a deployment.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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
```python
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. |
…Read the whole file at its exact version.
How to install
mdr add topoteretes/cognee/cognee-performance@sha256:463891ca174b2834The line at the top of this page pins the label git:20261014.421002d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ojekz5gcqt2dsl7w)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 29, 2026 and Oct 14, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.421002d latest | 2026-10-14 | 421002d | 9,999 B | A | view · diff |
| git:20261009.200aa80 | 2026-10-09 | 200aa80 | 9,999 B | A | view · diff |
| git:20261007.bf529e3 | 2026-10-07 | bf529e3 | 10,025 B | A | view · diff |
| git:20260929.6e7b2ca | 2026-09-29 | 6e7b2ca | 10,062 B | A | view · diff |
| git:20260929.d802d12 | 2026-09-29 | d802d12 | 10,063 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9999 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
topoteretes/cognee · 33,092 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ojekz5gcqt2dsl7w GET https://markdownregistry.com/api/v1/resolve?ref=topoteretes/cognee/cognee-performance GET https://markdownregistry.com/api/v1/blob/463891ca174b2834e1a688645c7926e5fc836f2f3d8862daaf0742338f436956
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.