One command to set up

~/my-project

$ cce init Code Context Engine · my-project ──────────────────────────────── ✓ Git hooks installed (3 hooks, auto-updates) ✓ MCP server registered in .mcp.json ✓ CLAUDE.md created ✓ .gitignore updated Indexing project... ██████████████████████████████ 89/89 files 100% ✓ Indexed 1,247 chunks from 89 files Done! Restart your AI coding agent to activate CCE.

30-second demo

terminal

CCE Demo: install, index, search, and see token savings

Benchmark

Reproducible results

20 real questions against FastAPI. No synthetic queries.

94% retrieval savings

89% compression

0.90 recall@10

0.4ms p50 latency

Token flow per query (avg)

Full files

83,681

After retrieval

4,927

After compression

523

Per-Layer Savings

Retrieval · measured 94%

Chunk Compression · measured 89%

Output Compression · estimated 65%

Grammar · measured 13%

Reproduce it

$ pip install "code-context-engine[local]"
$ python benchmarks/run_benchmark.py \
--repo https://github.com/fastapi/fastapi.git \
--source-dir fastapi

Full results: benchmarks/results/fastapi.md

Capabilities

What it does

AST-Aware Indexing

Tree-sitter parses your code into semantic chunks (functions, classes, modules). Stored locally with vector embeddings. Git hooks keep the index current after every commit.

$ cce init && cce index

Hybrid Search + Graph Expansion

Your agent calls context_search via MCP. Vector similarity + BM25 keyword search merged via Reciprocal Rank Fusion. If auth.py is a hit, utils.py it imports comes too.

context_search("how does auth work?")

Smart Compression

With Ollama running locally, chunks are summarized by phi3:mini. Without it, smart truncation extracts signatures and docstrings. Four output levels: off, lite, standard, max.

Session Memory

Decisions and code areas persist across sessions via record_decision, record_code_area, and session_recall. No re-explaining your architecture every time.

Dashboard + Savings Tracking

Every query is recorded. cce dashboard for charts and live polling. cce savings for token counts and dollar estimates from live Anthropic pricing.

Agent Plugin

cce init --plugin generates a portable Agent Plugin directory. VS Code, Cursor, Copilot, Codex, ChatGPT, and Kiro load it automatically via uvx. Zero install.

$ cce init --plugin

Feature	No tool	Caveman	CCE (default)	CCE + Ollama Best
Compress output tokens	✗	✓	✓	✓
Compress input tokens	✗	✗	✓	✓
Codebase indexing	✗	✗	✓	✓
Session memory	✗	✗	✓	✓
LLM summarization	✗	✗	✗	✓
Agent Plugin (zero-install)	✗	✗	✓	✓
Cost per session (Sonnet, medium project)	$0.45	$0.26	$0.14	$0.09