Llm Context
If you're building RAG pipelines or AI agents, this is your connector to Brave's search index. It skips the snippets and returns actual extracted web content: text chunks, tables, code blocks, all pre-ranked and ready to feed your LLM. The real power is in the Goggles feature, which lets you filter sources inline (official docs only, no paywalls, academic sources) so you control what grounds your model. You get granular knobs for token budgets and snippet counts, plus local search support when you need location-aware results. It's faster than their full answer engine and designed specifically for tool calls and agentic workflows. One oddity: the threshold modes (strict/balanced/lenient) affect relevance filtering, but you'll need to experiment to see what works for your use case.
- skills.sh installs
- 1.3K
- GitHub stars
- 196
- last updated
- Aug 21, 2026
Install
$ npx -y skills add brave/brave-search-skills --skill llm-context --agent claude-codeInstalls into .claude/skills of the current project.
Files
LLM Context
Requires API Key: Get one at https://api.search.brave.com
Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe
Brave LLM Context API delivers pre-extracted, relevance-ranked web content optimized for grounding LLM responses in real-time search results. Unlike traditional web search APIs that return links and snippets, LLM Context extracts the actual page content—text chunks, tables, code blocks, and structured data—so your LLM or AI agent can reason over it directly.
LLM Context vs AI Grounding
| Feature | LLM Context (this) | AI Grounding (answers) |
|---|---|---|
| Output | Raw extracted content for YOUR LLM | End-to-end AI answers with citations |
| Interface | REST API (GET/POST) | OpenAI-compatible /chat/completions |
| Searches | Single search per request | Multi-search (iterative research) |
| Speed | Fast (<1s) | Slower |
| Plan | Search | Answers |
| Endpoint | /res/v1/llm/context | /res/v1/chat/completions |
| Best for | AI agents, RAG pipelines, tool calls | Chat interfaces, research mode |
Endpoint
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/brave/brave-search-skills
- Category
- AI & Agent Building
- First seen
- Jun 3, 2026
More from brave/brave-search-skills
All 11Recommended
More AI & Agent Building
agent-uiinference-sh/skillsBatteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabi1.2Kskills.sh installs
agentic-jujutsuruvnet/rufloQuantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination1.2Kskills.sh installs
agent-supply-chaingithub/awesome-copilotVerify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests for agent plugins or 1.1Kskills.sh installsmcp-security-auditgithub/awesome-copilotAudit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP1.1Kskills.sh installs
agentic-gatewayalchemyplatform/skillsWire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402,1.1Kskills.sh installsllm-modelsinference-sh/skillsAccess Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro1.1Kskills.sh installs