Agent skill

Faiss

Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.

MITAuto-check passedDatabases

Install Faiss

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/faiss .claude/skills/faiss && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .claude/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/faiss .agents/skills/faiss && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .agents/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/faiss .cursor/skills/faiss && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .cursor/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/AlexAI-MCP/hermes-CCC.git --path skills/faiss

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/faiss .gemini/skills/faiss && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .gemini/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/faiss .github/skills/faiss && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .github/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC faiss --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/faiss .opencode/skills/faiss && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "faiss" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/faiss into .opencode/skills/faiss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "faiss", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: faiss
GitHub stars: 135
Token cost: ~1.1k tokens
SKILL.md length: 128 words
Files: 1
Skills in repo: 44
Repo updated: Apr 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.

Tasks that involve Vector databases
SKILL.md covers When to Use FAISS, Setup, Basic Flat Index (Exact Search) and Cosine Similarity (Normalize…, plus 6 more sections
Calls pip

What it does

Faiss is an agent skill from AlexAI-MCP/hermes-CCC. Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Vector databases. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

Tasks that involve Vector databases

Example prompts

“/faiss”

Requirements

Python 3
Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Faiss loads about 1.1k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~36
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 128 words, ~1,052 tokens.

Download SKILL.mdSave it as .claude/skills/faiss/SKILL.md (or your agent's skills folder).

name: faiss
description: Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.
version: 1.0.0
author: hermes-CCC (ported from Hermes Agent by NousResearch)
license: MIT

FAISS — Fast Vector Similarity Search

FAISS (Facebook AI Similarity Search) is a library for efficient similarity search over large collections of vectors. No server required — runs entirely in-process.

When to Use FAISS

Millions of vectors, need maximum speed
Can't run a server (embedded use case)
Research / prototyping at scale
Custom index types (HNSW, IVF, PQ)

Setup

bash

pip install faiss-cpu        # CPU only
pip install faiss-gpu        # GPU (requires CUDA)
pip install sentence-transformers numpy

Basic Flat Index (Exact Search)

python

import faiss
import numpy as np
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")  # dim=384
DIM = 384

# Build index
documents = [
    "Python async programming",
    "Machine learning with PyTorch",
    "Docker container management",
    "GraphQL API design",
]

embeddings = model.encode(documents).astype(np.float32)

# Flat L2 index (exact, brute force)
index = faiss.IndexFlatL2(DIM)
index.add(embeddings)
print(f"Index size: {index.ntotal}")

# Search
query = "how to do async in Python?"
q_vec = model.encode([query]).astype(np.float32)

distances, indices = index.search(q_vec, k=3)
for i, idx in enumerate(indices[0]):
    print(f"[{distances[0][i]:.3f}] {documents[idx]}")

Cosine Similarity (Normalize first)

python

# For cosine similarity: normalize vectors, use IndexFlatIP (inner product)
def normalize(vecs):
    norms = np.linalg.norm(vecs, axis=1, keepdims=True)
    return vecs / np.maximum(norms, 1e-8)

embeddings_norm = normalize(embeddings.astype(np.float32))
index_cos = faiss.IndexFlatIP(DIM)
index_cos.add(embeddings_norm)

q_norm = normalize(model.encode([query]).astype(np.float32))
scores, indices = index_cos.search(q_norm, k=3)

IVF Index (Fast Approximate Search)

python

# For large datasets (>100k vectors)
N_CLUSTERS = 100  # sqrt(N) is a good heuristic

quantizer = faiss.IndexFlatL2(DIM)
index_ivf = faiss.IndexIVFFlat(quantizer, DIM, N_CLUSTERS)

# Must train before adding
index_ivf.train(embeddings)
index_ivf.add(embeddings)
index_ivf.nprobe = 10  # search 10 clusters (higher = more accurate, slower)

distances, indices = index_ivf.search(q_vec, k=5)

HNSW Index (Best Speed/Accuracy Tradeoff)

python

index_hnsw = faiss.IndexHNSWFlat(DIM, 32)  # 32 = M parameter
index_hnsw.add(embeddings)

distances, indices = index_hnsw.search(q_vec, k=5)

Save and Load Index

python

# Save
faiss.write_index(index, "my_index.faiss")

# Load
index = faiss.read_index("my_index.faiss")

With Metadata (store separately)

python

import pickle

# FAISS only stores vectors — store metadata separately
metadata = [{"id": i, "text": doc} for i, doc in enumerate(documents)]

# Save both
faiss.write_index(index, "vectors.faiss")
with open("metadata.pkl", "wb") as f:
    pickle.dump(metadata, f)

# Load and query
index = faiss.read_index("vectors.faiss")
with open("metadata.pkl", "rb") as f:
    metadata = pickle.load(f)

distances, indices = index.search(q_vec, k=3)
for idx in indices[0]:
    print(metadata[idx]["text"])

GPU Acceleration

python

res = faiss.StandardGpuResources()
index_gpu = faiss.index_cpu_to_gpu(res, 0, index)  # GPU 0
distances, indices = index_gpu.search(q_vec, k=5)

Index Selection Guide

Index	Size	Speed	Accuracy	Use Case
IndexFlatL2	Any	Slow	100%	<100k vectors, exact needed
IndexFlatIP	Any	Slow	100%	Cosine similarity
IndexIVFFlat	Large	Fast	~95%	100k–10M vectors
IndexHNSWFlat	Medium	Very fast	~99%	Best general choice
IndexIVFPQ	Huge	Fastest	~90%	Billions, memory-constrained

Files

Just SKILL.md in skills/faiss of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Faiss next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Faiss compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Faiss this skillAlexAI-MCP/hermes-CCC	135	—	~1.1k	Automated safety check: Pass	MIT	6 mo ago
Codebase Explorationgiancarloerra/SocratiCode	3.3k	1 repos	~1.5k	Automated safety check: Pass	AGPL-3.0	2 days ago
FAISS Similarity SearchOrchestra-Research/AI-Research-SKILLs	13k	6 repos	~1.3k	Automated safety check: Pass	MIT	3 mo ago
Weaviateweaviate/agent-skills	104	—	~1.8k	Automated safety check: Pass	BSD-3-Clause	4 days ago
Pinecone Vector DatabaseOrchestra-Research/AI-Research-SKILLs	13k	5 repos	~2k	Automated safety check: Pass	MIT	3 mo ago
Qdrant Vector SearchOrchestra-Research/AI-Research-SKILLs	13k	4 repos	~3.4k	Automated safety check: Pass	MIT	3 mo ago

Similar skills

Codebase Exploration
giancarloerra/SocratiCode
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts.
3.3k GitHub starsUsed in 1 repo~1.5k tokens
DatabasesAuto-check passed
FAISS Similarity Search
Orchestra-Research/AI-Research-SKILLs
Sets up FAISS for fast nearest-neighbor search over large collections of dense vectors, choosing between Flat, IVF, HNSW and product quantization indexes.
13k GitHub starsUsed in 6 repos~1.3k tokens
DatabasesAuto-check passed
Weaviate
weaviate/agent-skills
Official
Search, query, and manage Weaviate vector database collections.
104 GitHub stars~1.8k tokensUpdated 4 days ago
DatabasesAuto-check passed
Pinecone Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to use Pinecone, a managed vector database, for production RAG, semantic search and recommendations: indexes, upserts, queries, filters and namespaces.
13k GitHub starsUsed in 5 repos~2k tokens
DatabasesAuto-check passed
Qdrant Vector Search
Orchestra-Research/AI-Research-SKILLs
Explains how to run Qdrant, a Rust vector database, for RAG and semantic search, covering collections, points, distance metrics and filtered or batched queries.
13k GitHub starsUsed in 4 repos~3.4k tokens
DatabasesAuto-check passed
Hyperspacedb Core
YARlabs/hyperspace-db
Core operations for HyperspaceDB — a multi-geometry vector database.
162 GitHub stars~1.5k tokensUpdated today
DatabasesAuto-check passed

Questions about Faiss

What does Faiss do?

Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server. Faiss is an agent skill from AlexAI-MCP/hermes-CCC. Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.

When should I use Faiss?

Faiss fits situations like: tasks that involve Vector databases.

How do I install Faiss in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a claude-code`. Or copy the skill folder (skills/faiss in AlexAI-MCP/hermes-CCC) into .claude/skills/faiss in your project. Claude Code loads it when a task matches its description.

How do I install Faiss in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a codex`. Or copy the skill folder (skills/faiss in AlexAI-MCP/hermes-CCC) into .agents/skills/faiss in your project. Codex loads it when a task matches its description.

Can I use Faiss in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill faiss -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/faiss, .gemini/skills/faiss, .github/skills/faiss and .opencode/skills/faiss in your project.

What does Faiss need to run?

Going by SKILL.md and its folder, Faiss needs the command-line tools its instructions call (pip). Our summary lists: Python 3; Docker.

Does Faiss access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Faiss safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Faiss use?

Faiss is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Faiss use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Faiss?

Skills that share tags, products or a category with Faiss: Codebase Exploration (giancarloerra/SocratiCode, 3.3k stars), FAISS Similarity Search (Orchestra-Research/AI-Research-SKILLs, 13k stars), Weaviate (weaviate/agent-skills, 104 stars) and Pinecone Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Faiss?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Faiss

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

FAISS — Fast Vector Similarity Search

When to Use FAISS

Setup

Basic Flat Index (Exact Search)

Cosine Similarity (Normalize first)

IVF Index (Fast Approximate Search)

HNSW Index (Best Speed/Accuracy Tradeoff)

Save and Load Index

With Metadata (store separately)

GPU Acceleration

Index Selection Guide

Files

Compare with similar skills

Similar skills

More from AlexAI-MCP/hermes-CCC

Related

Questions about Faiss