diff --git a/docs/index.md b/docs/index.md
index 0f51a9cce..08f9307d9 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,176 +1,372 @@
# Headroom
+
+
**The Context Optimization Layer for LLM Applications**
-Tool outputs are 70-95% redundant. Headroom compresses that away—without losing information.
+Compress everything your AI agent reads. Same answers, fraction of the tokens.
+
+
+
+
+
+[](https://pypi.org/project/headroom-ai/)
+[](https://pypi.org/project/headroom-ai/)
+[](https://github.com/chopratejas/headroom/blob/main/LICENSE)
+[](https://discord.gg/QEyNhaGA)
+
+
+
+
+
+
+87%
+Avg Token Reduction
+
+
+100%
+Answer Accuracy
+
+
+6
+Compression Algorithms
+
+
+100+
+LLM Providers
+
+
+
+
+
+
+### LangChain
+
+Wrap any chat model. Supports memory, retrievers, tools, streaming, async.
```python
-from headroom import compress
+from headroom.integrations import HeadroomChatModel
-# Compress messages before sending to LLM
-result = compress(messages, model="claude-sonnet-4-5-20250929")
-response = client.messages.create(
- model="claude-sonnet-4-5-20250929",
- messages=result.messages,
-)
-
-print(f"Saved {result.tokens_saved} tokens ({result.compression_ratio:.0%})")
+llm = HeadroomChatModel(ChatOpenAI(model="gpt-4o"))
```
----
+[LangChain Guide →](langchain.md)
-## Why Headroom?
+
-| Problem | Solution |
-|---------|----------|
-| Tool outputs bloat context with repetitive JSON | Statistical compression removes redundancy |
-| Dynamic content breaks provider caching | Cache alignment stabilizes prefixes |
-| Long conversations exceed context limits | Intelligent scoring drops low-value messages |
-| Compressed data might be needed later | CCR stores originals for on-demand retrieval |
+
----
+### Agno
-## Results
+Full agent framework integration with observability hooks.
-**100 log entries. One critical error buried at position 67.**
+```python
+from headroom.integrations.agno import HeadroomAgnoModel
-| Metric | Baseline | Headroom |
-|--------|----------|----------|
-| Input tokens | 10,144 | 1,260 |
-| Correct answers | 4/4 | 4/4 |
+model = HeadroomAgnoModel(Claude(id="claude-sonnet-4-20250514"))
+agent = Agent(model=model)
+```
-**87.6% fewer tokens. Same answer.**
+[Agno Guide →](agno.md)
-The FATAL error was automatically preserved—no configuration needed.
+
+
+
+
+### Strands
+
+Model wrapping + tool output hook provider for Strands Agents.
+
+```python
+from headroom.integrations.strands import HeadroomStrandsModel
+
+model = HeadroomStrandsModel(wrapped_model=bedrock_model)
+agent = Agent(model=model)
+```
+
+[Strands Guide →](strands.md)
+
+
+
+
+
+### MCP Tools
+
+Three tools for Claude Code, Cursor, or any MCP client: `headroom_compress`, `headroom_retrieve`, `headroom_stats`.
+
+```bash
+headroom mcp install && claude
+```
+
+[MCP Guide →](mcp.md)
+
+
+
+
-- Statistical JSON array compression (no hardcoded rules)
-- ML-based text compression via LLMLingua
-- AST-aware code compression
-- Image optimization (40-90% reduction)
+
+### Lossless Compression (CCR)
+Compresses aggressively, stores originals, gives the LLM a tool to retrieve full details. Nothing is thrown away.
+[Learn more →](ccr.md)
+
-**Context Management**
+
+### Smart Content Detection
+Auto-detects JSON, code, logs, text, diffs, HTML. Routes each to the best compressor. Zero configuration needed.
+[Learn more →](compression.md)
+
-- Intelligent message scoring and dropping
-- Compress-Cache-Retrieve (CCR) for lossless compression
-- Provider cache alignment for better hit rates
+
+### Cache Optimization
+Stabilizes prefixes so provider KV caches hit. Tracks frozen messages to preserve the 90% read discount.
+[Learn more →](ccr.md)
+
-**Operations**
+
+### Image Compression
+40-90% token reduction via trained ML router. Automatically selects resize/quality tradeoff per image.
+[Learn more →](image-compression.md)
+
-- Prometheus metrics endpoint
-- Request logging and cost tracking
-- Budget limits and rate limiting
+
+### Persistent Memory
+Hierarchical memory (user/session/agent/turn) with SQLite + HNSW backends. Survives across conversations.
+[Learn more →](memory.md)
+
+
+
+### Failure Learning
+Reads past sessions, finds failed tool calls, correlates with what succeeded, writes learnings to CLAUDE.md.
+[Learn more →](learn.md)
+
+
+
+### Multi-Agent Context
+Compress what moves between agents. Any framework.
+```python
+ctx = SharedContext()
+ctx.put("research", big_output)
+summary = ctx.get("research") # ~80% smaller
+```
+[Learn more →](shared-context.md)
+
+
+
+### Metrics & Observability
+Prometheus endpoint, per-request logging, cost tracking, budget limits, pipeline timing breakdowns.
+[Learn more →](metrics.md)
+
+
+