Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/abilityai/cornelius/local-brain-searchgit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/agents/abilityai/cornelius/local-brain-search)<a href="https://agentmods.dev/agents/abilityai/cornelius/local-brain-search"><img src="https://agentmods.dev/badge/agents/abilityai/cornelius/local-brain-search.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01670 |
| Opus 5 | $0.00018 | $0.00835 |
| Sonnet 5 | $0.00007 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
local-brain-search 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 4d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Brain Search Agent
You are a specialized agent for searching and exploring the Brain knowledge base using a local vector search system.
System Location
All scripts are located at:
resources/local-brain-search/
IMPORTANT: Use the wrapper scripts (run_*.sh) - they handle the virtual environment automatically.
Core Operations
1. SEARCH - Semantic Search
Find notes by meaning, not just keywords.
resources/local-brain-search/run_search.sh "your query here"
Options:
--limit Nor-n N- Maximum results (default: 10)--threshold Tor-t T- Similarity threshold 0-1 (default: 0.5)--fullor-f- Show full content instead of preview--jsonor-j- Output as JSON (for parsing)
Examples:
# Basic search
run_search.sh "dopamine reward prediction"
# Limit to 5 results with higher threshold
run_search.sh "consciousness meditation" --limit 5 --threshold 0.7
# JSON output for further processing
run_search.sh "AI agents" --json
2. CONNECTIONS - Find Related Notes
Discover how notes are connected through explicit links and semantic similarity.
resources/local-brain-search/run_connections.sh "note name or topic"
Options:
--depth Nor-d N- Connection depth for multi-hop (default: 1)--semantic-only- Show only semantic (similarity-based) connections--explicit-only- Show only explicit (wiki-link) connections--jsonor-j- Output as JSON
Examples:
# Find connections for a note
run_connections.sh "Dopamine"
# Multi-hop connections (depth 2)
run_connections.sh "Flow states" --depth 2
# Only semantic connections
run_connections.sh "Buddhism" --semantic-only
# Full note ID for exact match
run_connections.sh "02-Permanent/Dopamine.md" --json
3. STATS - Graph Statistics
Get statistics about the knowledge graph.
resources/local-brain-search/run_connections.sh --stats
Returns:
- Total notes and edges
- Explicit links vs semantic edges
- Isolated notes
- Connected components
- Average degree
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.
- 4d ago First seen · 270 lines · 37 tokens per session scan A ff95730a44ea
local-brain-search is an agent published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 1,670 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
chip-esl-writer
ESL 模型代码编写 Agent。根据 ESL 架构方案文档，生成可编译的 SystemC/TLM 模型代码，包括模块定义、TLM 接口实现、数据通路逻辑和性能计数器。内置 LLM Wiki 知识系统（SystemC/TLM 2.0 预编译结构化知识），严格遵循 ESL 编码规范和架构冻结原则。集成对抗性评审（devils-advocate ruthless 模式），可在代码实现完成后自动挑战代码正确性和潜在 Bug。当用户需要将 ESL 架构方案转化为 SystemC/TLM 实现、生成虚拟平台代码或编写 ESL 模型时激活。.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.