code-context-engine 0.4.18__tar.gz → 0.4.20__tar.gz

{code_context_engine-0.4.18 → code_context_engine-0.4.20}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: code-context-engine
-Version: 0.4.18
-Summary: Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode.
+Version: 0.4.20
+Summary: Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server.
 Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/elara-labs/code-context-engine
 Project-URL: Repository, https://github.com/elara-labs/code-context-engine
 Project-URL: Issues, https://github.com/elara-labs/code-context-engine/issues
-Keywords: claude,context,mcp,llm,code-indexing,vector-search
+Keywords: claude-code,save-tokens,token-savings,mcp-server,claude,cursor,code-indexing,reduce-ai-costs,llm,vector-search,ai-coding
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
@@ -21,7 +21,6 @@ License-File: LICENSE
 Requires-Dist: click>=8.1
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: sqlite-vec>=0.1.6
-Requires-Dist: fastembed>=0.4
 Requires-Dist: numpy>=1.24
 Requires-Dist: tree-sitter>=0.22
 Requires-Dist: tree-sitter-python>=0.21
@@ -44,7 +43,10 @@ Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
 Requires-Dist: pytest-aiohttp>=1.0; extra == "dev"
 Requires-Dist: pytest-cov>=5.0; extra == "dev"
 Requires-Dist: pytest-xdist>=3.5; extra == "dev"
+Requires-Dist: ruff>=0.13; extra == "dev"
 Provides-Extra: http
+Provides-Extra: local
+Requires-Dist: fastembed>=0.4; extra == "local"
 Dynamic: license-file
 
 <p align="center">
@@ -57,6 +59,10 @@ Dynamic: license-file
   <strong>Index your codebase. AI searches instead of re-reading files.<br>94% token savings, reproducibly benchmarked.</strong>
 </p>
 
+<p align="center">
+  <a href="https://elara-labs.github.io/code-context-engine/">Website</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html">Guide</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html">Benchmark</a> · <a href="https://github.com/elara-labs/code-context-engine">GitHub</a>
+</p>
+
 <br>
 
 <p align="center">
@@ -80,7 +86,8 @@ Dynamic: license-file
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Cursor-000?style=for-the-badge" alt="Cursor"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=for-the-badge&logo=google&logoColor=white" alt="Gemini CLI"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Codex_CLI-412991?style=for-the-badge" alt="Codex CLI"></a>&nbsp;
-  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>&nbsp;
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Tabnine-4B32C3?style=for-the-badge&logo=tabnine&logoColor=white" alt="Tabnine"></a>
 </p>
 
 <p align="center">
@@ -142,6 +149,12 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
 `cce init` auto-detects your editor and writes the right config:
@@ -154,6 +167,7 @@ Restart your editor. Done. Every question now hits the index instead of re-readi
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
 | OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
 | OpenCode | `opencode.json` | |
+| Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
@@ -196,7 +210,9 @@ With CCE:       context_search "payment flow"            =    800 tokens
 
 We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 source files, 180K tokens) with 20 real coding questions. No cherry-picking, no synthetic queries.
 
-**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression. This is conservative (agents often read more files than needed).
+**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression.
+
+**Important baseline note:** The 94% number is measured against full-file reads, not against what Claude Code actually does. In practice, Claude Code already uses grep, partial file reads, and targeted tools, so the real-world savings compared to normal Claude Code behavior will be lower than 94%. We use full-file as the baseline because it's reproducible and deterministic (no agent behavior variability). The benchmark measures CCE's retrieval efficiency, not a head-to-head comparison with Claude Code's built-in exploration.
 
 | Metric | Result |
 |--------|--------|
@@ -416,17 +432,18 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
 ## Supported Languages
 
-**AST-aware chunking (10 extensions):**
+**AST-aware chunking (tree-sitter parsed, 10 extensions):**
 
 | Language | Extensions |
 |----------|-----------|
@@ -438,7 +455,20 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 | Rust | `.rs` |
 | Java | `.java` |
 
-**Fallback chunking:** All other text files (Markdown, YAML, config, etc.) chunked by line range.
+**Language-aware fallback chunking (40+ extensions):**
+
+| Category | Languages |
+|----------|-----------|
+| Web | HTML, CSS, SCSS, LESS, Vue, Svelte |
+| Systems | C, C++, C#, Zig, Nim |
+| Mobile | Swift, Kotlin, Dart |
+| Functional | Haskell, Scala, Clojure, Elixir, Erlang, F# |
+| Scripting | Ruby, Perl, Lua, R, Bash/Zsh |
+| Data/Config | JSON, YAML, TOML, XML, SQL, GraphQL, Protobuf |
+| DevOps | Terraform, HCL, Dockerfile |
+| Docs | Markdown |
+
+All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
@@ -446,12 +476,14 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 | Page | Content |
 |------|---------|
+| [What is CCE? (Complete Guide)](https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html) | Setup, tools, how it works, FAQ |
+| [How to Save Claude Code Tokens](https://elara-labs.github.io/code-context-engine/blog/save-claude-code-tokens.html) | Cost breakdown and savings guide |
+| [Benchmark Deep Dive](https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html) | Full FastAPI benchmark methodology |
+| [Comparison with Alternatives](https://elara-labs.github.io/code-context-engine/comparison.html) | CCE vs Cursor, Aider, Continue, Greptile |
 | [Examples](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Examples.md) | Real conversations with Claude |
 | [How It Works](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/How-It-Works.md) | Full 9-stage pipeline |
 | [CLI Reference](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/CLI-Reference.md) | Every command with output |
 | [Configuration](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Configuration.md) | All config options |
-| [Project Commands](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Project-Commands.md) | Rules and preferences for Claude |
-| [Tech Stack](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Tech-Stack.md) | Every library and why |
 
 ---
 

code_context_engine-0.4.18/src/code_context_engine.egg-info/PKG-INFO → code_context_engine-0.4.20/README.md

@@ -1,52 +1,3 @@
-Metadata-Version: 2.4
-Name: code-context-engine
-Version: 0.4.18
-Summary: Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode.
-Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
-License-Expression: MIT
-Project-URL: Homepage, https://github.com/elara-labs/code-context-engine
-Project-URL: Repository, https://github.com/elara-labs/code-context-engine
-Project-URL: Issues, https://github.com/elara-labs/code-context-engine/issues
-Keywords: claude,context,mcp,llm,code-indexing,vector-search
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development :: Libraries
-Requires-Python: >=3.11
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: click>=8.1
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: sqlite-vec>=0.1.6
-Requires-Dist: fastembed>=0.4
-Requires-Dist: numpy>=1.24
-Requires-Dist: tree-sitter>=0.22
-Requires-Dist: tree-sitter-python>=0.21
-Requires-Dist: tree-sitter-javascript>=0.21
-Requires-Dist: tree-sitter-typescript>=0.21
-Requires-Dist: tree-sitter-php>=0.23
-Requires-Dist: tree-sitter-go>=0.23
-Requires-Dist: tree-sitter-rust>=0.23
-Requires-Dist: tree-sitter-java>=0.23
-Requires-Dist: watchdog>=4.0
-Requires-Dist: mcp>=1.0
-Requires-Dist: httpx>=0.27
-Requires-Dist: fastapi>=0.110
-Requires-Dist: uvicorn>=0.29
-Requires-Dist: aiohttp>=3.9
-Requires-Dist: psutil>=5.9
-Provides-Extra: dev
-Requires-Dist: pytest>=8.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
-Requires-Dist: pytest-aiohttp>=1.0; extra == "dev"
-Requires-Dist: pytest-cov>=5.0; extra == "dev"
-Requires-Dist: pytest-xdist>=3.5; extra == "dev"
-Provides-Extra: http
-Dynamic: license-file
-
 <p align="center">
   <img src="https://raw.githubusercontent.com/elara-labs/code-context-engine/main/docs/logo.svg" alt="Code Context Engine" width="140">
 </p>
@@ -57,6 +8,10 @@ Dynamic: license-file
   <strong>Index your codebase. AI searches instead of re-reading files.<br>94% token savings, reproducibly benchmarked.</strong>
 </p>
 
+<p align="center">
+  <a href="https://elara-labs.github.io/code-context-engine/">Website</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html">Guide</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html">Benchmark</a> · <a href="https://github.com/elara-labs/code-context-engine">GitHub</a>
+</p>
+
 <br>
 
 <p align="center">
@@ -80,7 +35,8 @@ Dynamic: license-file
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Cursor-000?style=for-the-badge" alt="Cursor"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=for-the-badge&logo=google&logoColor=white" alt="Gemini CLI"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Codex_CLI-412991?style=for-the-badge" alt="Codex CLI"></a>&nbsp;
-  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>&nbsp;
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Tabnine-4B32C3?style=for-the-badge&logo=tabnine&logoColor=white" alt="Tabnine"></a>
 </p>
 
 <p align="center">
@@ -142,6 +98,12 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
 `cce init` auto-detects your editor and writes the right config:
@@ -154,6 +116,7 @@ Restart your editor. Done. Every question now hits the index instead of re-readi
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
 | OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
 | OpenCode | `opencode.json` | |
+| Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
@@ -196,7 +159,9 @@ With CCE:       context_search "payment flow"            =    800 tokens
 
 We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 source files, 180K tokens) with 20 real coding questions. No cherry-picking, no synthetic queries.
 
-**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression. This is conservative (agents often read more files than needed).
+**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression.
+
+**Important baseline note:** The 94% number is measured against full-file reads, not against what Claude Code actually does. In practice, Claude Code already uses grep, partial file reads, and targeted tools, so the real-world savings compared to normal Claude Code behavior will be lower than 94%. We use full-file as the baseline because it's reproducible and deterministic (no agent behavior variability). The benchmark measures CCE's retrieval efficiency, not a head-to-head comparison with Claude Code's built-in exploration.
 
 | Metric | Result |
 |--------|--------|
@@ -416,17 +381,18 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
 ## Supported Languages
 
-**AST-aware chunking (10 extensions):**
+**AST-aware chunking (tree-sitter parsed, 10 extensions):**
 
 | Language | Extensions |
 |----------|-----------|
@@ -438,7 +404,20 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 | Rust | `.rs` |
 | Java | `.java` |
 
-**Fallback chunking:** All other text files (Markdown, YAML, config, etc.) chunked by line range.
+**Language-aware fallback chunking (40+ extensions):**
+
+| Category | Languages |
+|----------|-----------|
+| Web | HTML, CSS, SCSS, LESS, Vue, Svelte |
+| Systems | C, C++, C#, Zig, Nim |
+| Mobile | Swift, Kotlin, Dart |
+| Functional | Haskell, Scala, Clojure, Elixir, Erlang, F# |
+| Scripting | Ruby, Perl, Lua, R, Bash/Zsh |
+| Data/Config | JSON, YAML, TOML, XML, SQL, GraphQL, Protobuf |
+| DevOps | Terraform, HCL, Dockerfile |
+| Docs | Markdown |
+
+All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
@@ -446,12 +425,14 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 | Page | Content |
 |------|---------|
+| [What is CCE? (Complete Guide)](https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html) | Setup, tools, how it works, FAQ |
+| [How to Save Claude Code Tokens](https://elara-labs.github.io/code-context-engine/blog/save-claude-code-tokens.html) | Cost breakdown and savings guide |
+| [Benchmark Deep Dive](https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html) | Full FastAPI benchmark methodology |
+| [Comparison with Alternatives](https://elara-labs.github.io/code-context-engine/comparison.html) | CCE vs Cursor, Aider, Continue, Greptile |
 | [Examples](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Examples.md) | Real conversations with Claude |
 | [How It Works](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/How-It-Works.md) | Full 9-stage pipeline |
 | [CLI Reference](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/CLI-Reference.md) | Every command with output |
 | [Configuration](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Configuration.md) | All config options |
-| [Project Commands](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Project-Commands.md) | Rules and preferences for Claude |
-| [Tech Stack](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Tech-Stack.md) | Every library and why |
 
 ---
 

{code_context_engine-0.4.18 → code_context_engine-0.4.20}/pyproject.toml

@@ -1,14 +1,14 @@
 [project]
 name = "code-context-engine"
-version = "0.4.18"
-description = "Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode."
+version = "0.4.20"
+description = "Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server."
 readme = {file = "README.md", content-type = "text/markdown"}
 license = "MIT"
 authors = [
     {name = "Fazle Elahee", email = "felahee@gmail.com"},
     {name = "Raj", email = "rajkumar.sakti@gmail.com"},
 ]
-keywords = ["claude", "context", "mcp", "llm", "code-indexing", "vector-search"]
+keywords = ["claude-code", "save-tokens", "token-savings", "mcp-server", "claude", "cursor", "code-indexing", "reduce-ai-costs", "llm", "vector-search", "ai-coding"]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
@@ -23,7 +23,6 @@ dependencies = [
     "click>=8.1",
     "pyyaml>=6.0",
     "sqlite-vec>=0.1.6",
-    "fastembed>=0.4",
     "numpy>=1.24",
     "tree-sitter>=0.22",
     "tree-sitter-python>=0.21",
@@ -57,8 +56,14 @@ dev = [
     "pytest-aiohttp>=1.0",
     "pytest-cov>=5.0",
     "pytest-xdist>=3.5",
+    "ruff>=0.13",
 ]
 http = []  # back-compat: aiohttp is now a core dependency
+# Local on-device embedding via fastembed (ONNX). ~172 MB install
+# footprint; needed only if you don't have Ollama running. Without
+# this extra, CCE auto-detects Ollama at localhost:11434 and uses
+# nomic-embed-text via /api/embed.
+local = ["fastembed>=0.4"]
 
 [project.scripts]
 cce = "context_engine.cli:main"
@@ -94,4 +99,33 @@ dev = [
     "pytest-asyncio>=1.3.0",
     "pytest-aiohttp>=1.0",
     "pytest-xdist>=3.5",
+    "ruff>=0.13",
 ]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+extend-exclude = ["dist", "build", ".venv"]
+
+[tool.ruff.lint]
+# Default ruleset — pycodestyle errors (E) + pyflakes (F). Conservative
+# starting point; can be expanded later (I/imports, B/bugbear, UP/pyupgrade)
+# once the team is comfortable with the baseline. Selected rules are the
+# ones that catch real bugs (unused imports, undefined names, redefined
+# symbols) rather than stylistic preferences.
+select = ["E", "F", "W"]
+# E501 (line-too-long) is enforced via `line-length` above; default is 88
+# but we use 100 to match the existing codebase. Ignore a few rules that
+# are noisy in async/test code:
+ignore = [
+    "E501",  # line-too-long: handled by formatter, not all old code wrapped
+    "E402",  # module-import-not-at-top: legitimate inside conditional imports
+    "E741",  # ambiguous-variable-name (l/I/O): one-off in third-party-style code
+]
+
+[tool.ruff.lint.per-file-ignores]
+# Tests import fixtures and helpers that look unused but trigger collection.
+"tests/**" = ["F811"]
+# __init__.py files are allowed to re-export (those imports look unused but
+# are part of the public surface of the package).
+"**/__init__.py" = ["F401"]

code_context_engine-0.4.18/README.md → code_context_engine-0.4.20/src/code_context_engine.egg-info/PKG-INFO

@@ -1,3 +1,54 @@
+Metadata-Version: 2.4
+Name: code-context-engine
+Version: 0.4.20
+Summary: Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server.
+Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/elara-labs/code-context-engine
+Project-URL: Repository, https://github.com/elara-labs/code-context-engine
+Project-URL: Issues, https://github.com/elara-labs/code-context-engine/issues
+Keywords: claude-code,save-tokens,token-savings,mcp-server,claude,cursor,code-indexing,reduce-ai-costs,llm,vector-search,ai-coding
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click>=8.1
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: sqlite-vec>=0.1.6
+Requires-Dist: numpy>=1.24
+Requires-Dist: tree-sitter>=0.22
+Requires-Dist: tree-sitter-python>=0.21
+Requires-Dist: tree-sitter-javascript>=0.21
+Requires-Dist: tree-sitter-typescript>=0.21
+Requires-Dist: tree-sitter-php>=0.23
+Requires-Dist: tree-sitter-go>=0.23
+Requires-Dist: tree-sitter-rust>=0.23
+Requires-Dist: tree-sitter-java>=0.23
+Requires-Dist: watchdog>=4.0
+Requires-Dist: mcp>=1.0
+Requires-Dist: httpx>=0.27
+Requires-Dist: fastapi>=0.110
+Requires-Dist: uvicorn>=0.29
+Requires-Dist: aiohttp>=3.9
+Requires-Dist: psutil>=5.9
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: pytest-aiohttp>=1.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: pytest-xdist>=3.5; extra == "dev"
+Requires-Dist: ruff>=0.13; extra == "dev"
+Provides-Extra: http
+Provides-Extra: local
+Requires-Dist: fastembed>=0.4; extra == "local"
+Dynamic: license-file
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/elara-labs/code-context-engine/main/docs/logo.svg" alt="Code Context Engine" width="140">
 </p>
@@ -8,6 +59,10 @@
   <strong>Index your codebase. AI searches instead of re-reading files.<br>94% token savings, reproducibly benchmarked.</strong>
 </p>
 
+<p align="center">
+  <a href="https://elara-labs.github.io/code-context-engine/">Website</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html">Guide</a> · <a href="https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html">Benchmark</a> · <a href="https://github.com/elara-labs/code-context-engine">GitHub</a>
+</p>
+
 <br>
 
 <p align="center">
@@ -31,7 +86,8 @@
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Cursor-000?style=for-the-badge" alt="Cursor"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=for-the-badge&logo=google&logoColor=white" alt="Gemini CLI"></a>&nbsp;
   <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Codex_CLI-412991?style=for-the-badge" alt="Codex CLI"></a>&nbsp;
-  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/OpenCode-22C55E?style=for-the-badge&logo=gnometerminal&logoColor=white" alt="OpenCode"></a>&nbsp;
+  <a href="#install-and-see-savings-in-60-seconds"><img src="https://img.shields.io/badge/Tabnine-4B32C3?style=for-the-badge&logo=tabnine&logoColor=white" alt="Tabnine"></a>
 </p>
 
 <p align="center">
@@ -93,6 +149,12 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
 `cce init` auto-detects your editor and writes the right config:
@@ -105,6 +167,7 @@ Restart your editor. Done. Every question now hits the index instead of re-readi
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
 | OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
 | OpenCode | `opencode.json` | |
+| Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
@@ -147,7 +210,9 @@ With CCE:       context_search "payment flow"            =    800 tokens
 
 We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 source files, 180K tokens) with 20 real coding questions. No cherry-picking, no synthetic queries.
 
-**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression. This is conservative (agents often read more files than needed).
+**Methodology:** For each query, "without CCE" means reading the full content of every file the query touches. "With CCE" means the relevant chunks after compression.
+
+**Important baseline note:** The 94% number is measured against full-file reads, not against what Claude Code actually does. In practice, Claude Code already uses grep, partial file reads, and targeted tools, so the real-world savings compared to normal Claude Code behavior will be lower than 94%. We use full-file as the baseline because it's reproducible and deterministic (no agent behavior variability). The benchmark measures CCE's retrieval efficiency, not a head-to-head comparison with Claude Code's built-in exploration.
 
 | Metric | Result |
 |--------|--------|
@@ -367,17 +432,18 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
 ## Supported Languages
 
-**AST-aware chunking (10 extensions):**
+**AST-aware chunking (tree-sitter parsed, 10 extensions):**
 
 | Language | Extensions |
 |----------|-----------|
@@ -389,7 +455,20 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 | Rust | `.rs` |
 | Java | `.java` |
 
-**Fallback chunking:** All other text files (Markdown, YAML, config, etc.) chunked by line range.
+**Language-aware fallback chunking (40+ extensions):**
+
+| Category | Languages |
+|----------|-----------|
+| Web | HTML, CSS, SCSS, LESS, Vue, Svelte |
+| Systems | C, C++, C#, Zig, Nim |
+| Mobile | Swift, Kotlin, Dart |
+| Functional | Haskell, Scala, Clojure, Elixir, Erlang, F# |
+| Scripting | Ruby, Perl, Lua, R, Bash/Zsh |
+| Data/Config | JSON, YAML, TOML, XML, SQL, GraphQL, Protobuf |
+| DevOps | Terraform, HCL, Dockerfile |
+| Docs | Markdown |
+
+All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
@@ -397,12 +476,14 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 | Page | Content |
 |------|---------|
+| [What is CCE? (Complete Guide)](https://elara-labs.github.io/code-context-engine/blog/what-is-code-context-engine.html) | Setup, tools, how it works, FAQ |
+| [How to Save Claude Code Tokens](https://elara-labs.github.io/code-context-engine/blog/save-claude-code-tokens.html) | Cost breakdown and savings guide |
+| [Benchmark Deep Dive](https://elara-labs.github.io/code-context-engine/blog/benchmark-fastapi.html) | Full FastAPI benchmark methodology |
+| [Comparison with Alternatives](https://elara-labs.github.io/code-context-engine/comparison.html) | CCE vs Cursor, Aider, Continue, Greptile |
 | [Examples](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Examples.md) | Real conversations with Claude |
 | [How It Works](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/How-It-Works.md) | Full 9-stage pipeline |
 | [CLI Reference](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/CLI-Reference.md) | Every command with output |
 | [Configuration](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Configuration.md) | All config options |
-| [Project Commands](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Project-Commands.md) | Rules and preferences for Claude |
-| [Tech Stack](https://github.com/elara-labs/code-context-engine/blob/main/docs/wiki/Tech-Stack.md) | Every library and why |
 
 ---
 

{code_context_engine-0.4.18 → code_context_engine-0.4.20}/src/code_context_engine.egg-info/SOURCES.txt

@@ -47,6 +47,7 @@ src/context_engine/integration/session_capture.py
 src/context_engine/memory/__init__.py
 src/context_engine/memory/compressor.py
 src/context_engine/memory/db.py
+src/context_engine/memory/decision_extractor.py
 src/context_engine/memory/extractive.py
 src/context_engine/memory/grammar.py
 src/context_engine/memory/hook_installer.py

{code_context_engine-0.4.18 → code_context_engine-0.4.20}/src/code_context_engine.egg-info/requires.txt

@@ -1,7 +1,6 @@
 click>=8.1
 pyyaml>=6.0
 sqlite-vec>=0.1.6
-fastembed>=0.4
 numpy>=1.24
 tree-sitter>=0.22
 tree-sitter-python>=0.21
@@ -25,5 +24,9 @@ pytest-asyncio>=0.23
 pytest-aiohttp>=1.0
 pytest-cov>=5.0
 pytest-xdist>=3.5
+ruff>=0.13
 
 [http]
+
+[local]
+fastembed>=0.4