I ran ripgrep, Serena, claude-context and my own tool on the same repo
There are a lot of ways to let a coding agent find code now. Plain grep, a language server behind MCP, a vector database, a local index. Every README says its way is the right one, so I wanted to see them do the same job on the same code.
I build one of these tools, Semlith, so treat my bias accordingly. That's also why I'm showing the questions it got wrong.
The setup is Flask 3.1.3 on an M1 MacBook Air with 8 GB. Versions are ripgrep 15.2.0, Serena 2.1.0, claude-context 0.1.15 (with Milvus 3.0.3 and Ollama running nomic-embed-text) and semlith 0.50.0.
git clone --depth 1 --branch 3.1.3 https://github.com/pallets/flask && cd flask
The four approaches in one table
| | ripgrep | Serena | claude-context | Semlith |
|---|---|---|---|---|
| What it is | Text search, no index | Language servers behind MCP | Embeddings in Milvus | Local index, embeddings plus keyword plus code graph |
| Finds code by meaning | No | No | Yes | Yes |
| Edits code | No | Yes, by symbol | No | No, read only |
| Setup on Flask | Nothing | 30.9 s to index | About 21 min (CPU in Docker) | 84.3 s to index |
| Moving parts | One binary | Python env plus language servers | Docker, Milvus, Ollama, npx | One binary |
| Reads PDF, Word, Excel | No | No | No | Yes |
The rest of this post is how I got those numbers.
ripgrep, when you know the name
When the agent already knows the identifier, nothing beats grep.
rg -n max_content_length src
src/flask/wrappers.py:55: _max_content_length: int | None = None
src/flask/wrappers.py:60: def max_content_length(self) -> int | None:
src/flask/wrappers.py:80: if self._max_content_length is not None:
src/flask/wrappers.py:81: return self._max_content_length
src/flask/wrappers.py:84: return super().max_content_length
src/flask/wrappers.py:88: @max_content_length.setter
src/flask/wrappers.py:89: def max_content_length(self, value: int | None) -> None:
src/flask/wrappers.py:90: self._max_content_length = value
Eight lines, all of them right, in milliseconds.
Now ask the same thing the way a person would, without the name. An agent turns "limit how big an uploaded request body can be" into words and greps for them.
rg -n -i "upload|big" src
src/flask/cli.py:297: a bigger role. Typically it's created automatically by the
src/flask/helpers.py:542: @app.route("/uploads/<path:name>")
src/flask/helpers.py:545: app.config['UPLOAD_FOLDER'], name, as_attachment=True
src/flask/helpers.py:549: files or uploads. Uses :func:`~werkzeug.security.safe_join` to
None of these is the answer, because wrappers.py never says "upload" or "big". This is where an agent starts guessing more words and opening more files.
Serena, when you want a language server
Serena gives the agent symbol tools backed by real language servers, over 40 languages. Since version 2 it shows up as a REPL, so the agent writes a little Python against Serena's API.
uv venv -p 3.11 venv-serena
uv pip install -p venv-serena "serena-agent @ git+https://github.com/oraios/serena@v2.1.0"
serena project index .
Indexing took 30.9 seconds. Given the name, it's precise.
s.lsp.find_symbol("max_content_length")
# [{"name_path": "Request/max_content_length", "kind": "Method",
# "relative_path": "src/flask/wrappers.py", "body_location": {"start_line": 87, ...}}]
References come back in about 2 seconds and they come from the language server, so they are real references, not text matches. Line numbers count from zero, which caught me out the first time.
Without the name though, Serena falls back to a regex pattern search, and that returns the same lines grep did.
s.fs.search_for_pattern("upload|big", relative_path="src")
The thing Serena does that none of the others do is edit. Replace a function body, insert after a symbol, rename across files. If your agent spends most of its time changing code it already found, that's a real advantage.
claude-context, run fully local
claude-context is Zilliz's MCP server. It chunks code, embeds it and stores the vectors in Milvus, with hybrid search on top. By default it wants an OpenAI key for embeddings and a Zilliz Cloud key for the database. It also supports a fully local setup, so that's what I ran.
curl -sSL https://github.com/milvus-io/milvus/releases/download/v3.0.3/milvus-standalone-docker-compose.yaml -o docker-compose.yaml
docker compose up -d
docker run -d --name cc-ollama --cpus=4 -p 127.0.0.1:11434:11434 ollama/ollama:0.40.13
docker exec cc-ollama ollama pull nomic-embed-text
EMBEDDING_PROVIDER=Ollama EMBEDDING_MODEL=nomic-embed-text \
OLLAMA_HOST=http://127.0.0.1:11434 MILVUS_ADDRESS=localhost:19530 \
npx -y @zilliz/claude-context-mcp@0.1.15
The images came to 6.14 GB and the first npx start pulled 418 MB of packages. While it worked I watched its connections, and it only talked to Milvus and Ollama on the machine.
Two things bit me. On the first run Milvus exited mid-index while Ollama had every CPU, so I capped Ollama at four. The second one is worth knowing if you use it. get_indexing_status said this at 92 seconds.
✅ Codebase '…/flask' is fully indexed and ready for search.
📊 Statistics: 100 files, 100 chunks
It wasn't done. The server's own log finished at 1,266.9 seconds with 86 files and 1,837 chunks. If your agent trusts that status and searches early, it searches a partial index without knowing.
That 21 minutes isn't a fair speed test either. Docker on a Mac has no GPU access, so Ollama embedded on the CPU. A native Ollama install would be quicker, I just didn't measure it.
Semlith, the one I build
semlith index .
indexed 211 files (2778 chunks, 5 images) in 84.3s — 0 already indexed, 4 skipped (4 empty), 0 removed
That count includes the .rst docs, which claude-context skips by default. Serena was quicker to set up here, since it doesn't embed anything.
!Horizontal bar chart of the time to index Flask 3.1.3 before the first search. ripgrep needs no index, Serena takes 30.9 seconds, Semlith 84.3 seconds and claude-context 1,266.9 seconds with Ollama embedding on the CPU in Docker.
Setup time on the same checkout. Serena was the quickest of the indexed tools, and claude-context's time is CPU-only embedding in Docker.
semlith search -k 5 "limit how big an uploaded request body can be"
1. 0.087 vf src/flask/wrappers.py:59-71
2. 0.083 vf src/flask/wrappers.py:91-106
3. 0.077 v docs/web-security.rst:26-38
4. 0.076 vf docs/patterns/fileuploads.rst:135-153
5. 0.072 vf src/flask/wrappers.py:105-123
5 hits in 360.027667ms
The first hit is the property. The letters after the score say how it was found, v for the vector list and f for the keyword list.
The question everyone got wrong
I asked all of them where Flask decides which error handler runs for an exception. The answer is _find_error_handler in src/flask/sansio/app.py.
Grep did best. rg -n -i "error handler" src lands on line 826 of that file, the function's docstring, because the question uses the same words the code does.
Semlith's top five were all in docs/errorhandling.rst. Those pages explain the order Flask uses, so they answer the question, but they aren't the code. claude-context had the function at rank 8.
So "semantic search beats grep" isn't true in general. When the question already uses the code's own words, grep is very hard to beat.
Bigger samples
Three questions on one repo prove nothing, so here's what I could measure at scale.
On SWE-bench Verified, 500 real GitHub issues, the issue text is the query and the gold is every file the fix edits. Semlith had a right file in its top 10 for 76.8% of them, against 47.0% for one ripgrep pass ranked and read in order. That's retrieval only, not whether an agent then fixes the bug.
On 20 issues from SWE-bench Lite, every tool got the same checkout and issue text. Serena 1.7.0 finished 16 of 20 (4 timed out) and had the right file in its top 5 for 25.0% of those, against 56.2% for Semlith on the same 16. That run predates Serena's REPL, so 2.1.0 might do differently. claude-context isn't in that comparison yet, so I won't give it a number.
And the one that keeps me honest. On 50 questions about a single unfamiliar repo, headless Claude Code on Opus scored 92% with grep alone and 92% with Semlith installed beside it. A strong agent with room to explore gets there with grep.
What each one costs before you use it
Every MCP server sends its tool definitions at session start, and the agent pays for them on every turn. I counted the tools/list result at about four bytes a token.
Serena tools: 2 4544 bytes, about 1136 tokens
semlith tools: 8 2668 bytes, about 667 tokens
Both are small. Serena keeps the list short with a REPL, then the agent reads 9,292 characters of instructions when it calls initial_instructions.
Which I'd pick
Honestly they do different jobs, and you can run more than one.
- One repo, a strong model, names you mostly know. Grep is enough.
- An agent that edits a lot by symbol. Serena.
- You already run Milvus or Zilliz Cloud, or want to pick the embedding provider. claude-context.
- Many repos, documents next to the code, nothing to sign up for. That's the case I built Semlith for.
The full runs with every command are on semlith.com and the benchmark harness is in the repo at semlith/semlith.
What are you using for code search with your agents right now, and where does it fall over?
1 reaction · 1 comment
Mentions
GPL-3.0, 249 contributors. Helps anyone running agents on big, multi-file codebases. Honest limit: some languages need extra installs, and on tiny edits your agent's built-ins are just as good. #OpenSource oraios/serena
I ran ripgrep, Serena, claude-context and my own tool on the same repo There are a lot of ways to let a coding agent find code now. Plain grep, a language server behind MCP, a vector database, a local index. Every README says its way is the right one, so I wanted to see them do the same job on the same code. I build one of these tools, Semlith, so treat my bias accordingly. That's also why I'm showing the questions it got wrong. The setup is Flask 3.1.3 on an M1 MacBook Air with 8 GB. Versions are ripgrep 15.2.0, Serena 2.1.0, claude-context 0.1.15 (with Milvus 3.0.3 and Ollama running nomic-embed-text) and semlith 0.50.0. git clone --depth 1 --branch 3.1.3 https://github.com/pallets/flask && cd flask The four approaches in one table | | ripgrep | Serena | claude-context | Semlith | |---|---|---|---|---| | What it is | Text search, no index | Language servers behind MCP | Embeddings in Milvus | Local index, embeddings plus keyword plus code graph | | Finds code by meaning | No | No | Yes | Yes | | Edits code | No | Yes, by symbol | No | No, read only | | Setup on Flask | Nothing | 30.9 s to index | About 21 min (CPU in Docker) | 84.3 s to index | | Moving parts | One binary | Python env plus language servers | Docker, Milvus, Ollama, npx | One binary | | Reads PDF, Word, Excel | No | No | No | Yes | The rest of this post is how I got those numbers. ripgrep, when you know the name When the agent already knows the identifier, nothing beats grep. rg -n max_content_length src src/flask/wrappers.py:55: _max_content_length: int | None = None src/flask/wrappers.py:60: def max_content_length(self) -> int | None: src/flask/wrappers.py:80: if self._max_content_length is not None: src/flask/wrappers.py:81: return self._max_content_length src/flask/wrappers.py:84: return super().max_content_length src/flask/wrappers.py:88: @max_content_length.setter src/flask/wrappers.py:89: def max_content_length(self, value: int | None) -> None: src/flask/wrappers.py:90: self._max_content_length = value Eight lines, all of them right, in milliseconds. Now ask the same thing the way a person would, without the name. An agent turns "limit how big an uploaded request body can be" into words and greps for them. rg -n -i "upload|big" src src/flask/cli.py:297: a bigger role. Typically it's created automatically by the src/flask/helpers.py:542: @app.route("/uploads/<path:name>") src/flask/helpers.py:545: app.config['UPLOAD_FOLDER'], name, as_attachment=True src/flask/helpers.py:549: files or uploads. Uses :func:`~werkzeug.security.safe_join` to None of these is the answer, because wrappers.py never says "upload" or "big". This is where an agent starts guessing more words and opening more files. Serena, when you want a language server Serena gives the agent symbol tools backed by real language servers, over 40 languages. Since version 2 it shows up as a REPL, so the agent writes a little Python against Serena's API. uv venv -p 3.11 venv-serena uv pip install -p venv-serena "serena-agent @ git+https://github.com/oraios/serena@v2.1.0" serena project index . Indexing took 30.9 seconds. Given the name, it's precise. s.lsp.find_symbol("max_content_length") # [{"name_path": "Request/max_content_length", "kind": "Method", # "relative_path": "src/flask/wrappers.py", "body_location": {"start_line": 87, ...}}] References come back in about 2 seconds and they come from the language server, so they are real references, not text matches. Line numbers count from zero, which caught me out the first time. Without the name though, Serena falls back to a regex pattern search, and that returns the same lines grep did. s.fs.search_for_pattern("upload|big", relative_path="src") The thing Serena does that none of the others do is edit. Replace a function body, insert after a symbol, rename across files. If your agent spends most of its time changing code it already found, that's a real advantage. claude-context, run fully local claude-context is Zilliz's MCP server. It chunks code, embeds it and stores the vectors in Milvus, with hybrid search on top. By default it wants an OpenAI key for embeddings and a Zilliz Cloud key for the database. It also supports a fully local setup, so that's what I ran. curl -sSL https://github.com/milvus-io/milvus/releases/download/v3.0.3/milvus-standalone-docker-compose.yaml -o docker-compose.yaml docker compose up -d docker run -d --name cc-ollama --cpus=4 -p 127.0.0.1:11434:11434 ollama/ollama:0.40.13 docker exec cc-ollama ollama pull nomic-embed-text EMBEDDING_PROVIDER=Ollama EMBEDDING_MODEL=nomic-embed-text \ OLLAMA_HOST=http://127.0.0.1:11434 MILVUS_ADDRESS=localhost:19530 \ npx -y @zilliz/claude-context-mcp@0.1.15 The images came to 6.14 GB and the first npx start pulled 418 MB of packages. While it worked I watched its connections, and it only talked to Milvus and Ollama on the machine. Two things bit me. On the first run Milvus exited mid-index while Ollama had every CPU, so I capped Ollama at four. The second one is worth knowing if you use it. get_indexing_status said this at 92 seconds. ✅ Codebase '…/flask' is fully indexed and ready for search. 📊 Statistics: 100 files, 100 chunks It wasn't done. The server's own log finished at 1,266.9 seconds with 86 files and 1,837 chunks. If your agent trusts that status and searches early, it searches a partial index without knowing. That 21 minutes isn't a fair speed test either. Docker on a Mac has no GPU access, so Ollama embedded on the CPU. A native Ollama install would be quicker, I just didn't measure it. Semlith, the one I build semlith index . indexed 211 files (2778 chunks, 5 images) in 84.3s — 0 already indexed, 4 skipped (4 empty), 0 removed That count includes the .rst docs, which claude-context skips by default. Serena was quicker to set up here, since it doesn't embed anything. !Horizontal bar chart of the time to index Flask 3.1.3 before the first search. ripgrep needs no index, Serena takes 30.9 seconds, Semlith 84.3 seconds and claude-context 1,266.9 seconds with Ollama embedding on the CPU in Docker. Setup time on the same checkout. Serena was the quickest of the indexed tools, and claude-context's time is CPU-only embedding in Docker. semlith search -k 5 "limit how big an uploaded request body can be" 1. 0.087 vf src/flask/wrappers.py:59-71 2. 0.083 vf src/flask/wrappers.py:91-106 3. 0.077 v docs/web-security.rst:26-38 4. 0.076 vf docs/patterns/fileuploads.rst:135-153 5. 0.072 vf src/flask/wrappers.py:105-123 5 hits in 360.027667ms The first hit is the property. The letters after the score say how it was found, v for the vector list and f for the keyword list. The question everyone got wrong I asked all of them where Flask decides which error handler runs for an exception. The answer is _find_error_handler in src/flask/sansio/app.py. Grep did best. rg -n -i "error handler" src lands on line 826 of that file, the function's docstring, because the question uses the same words the code does. Semlith's top five were all in docs/errorhandling.rst. Those pages explain the order Flask uses, so they answer the question, but they aren't the code. claude-context had the function at rank 8. So "semantic search beats grep" isn't true in general. When the question already uses the code's own words, grep is very hard to beat. Bigger samples Three questions on one repo prove nothing, so here's what I could measure at scale. On SWE-bench Verified, 500 real GitHub issues, the issue text is the query and the gold is every file the fix edits. Semlith had a right file in its top 10 for 76.8% of them, against 47.0% for one ripgrep pass ranked and read in order. That's retrieval only, not whether an agent then fixes the bug. On 20 issues from SWE-bench Lite, every tool got the same checkout and issue text. Serena 1.7.0 finished 16 of 20 (4 timed out) and had the right file in its top 5 for 25.0% of those, against 56.2% for Semlith on the same 16. That run predates Serena's REPL, so 2.1.0 might do differently. claude-context isn't in that comparison yet, so I won't give it a number. And the one that keeps me honest. On 50 questions about a single unfamiliar repo, headless Claude Code on Opus scored 92% with grep alone and 92% with Semlith installed beside it. A strong agent with room to explore gets there with grep. What each one costs before you use it Every MCP server sends its tool definitions at session start, and the agent pays for them on every turn. I counted the tools/list result at about four bytes a token. Serena tools: 2 4544 bytes, about 1136 tokens semlith tools: 8 2668 bytes, about 667 tokens Both are small. Serena keeps the list short with a REPL, then the agent reads 9,292 characters of instructions when it calls initial_instructions. Which I'd pick Honestly they do different jobs, and you can run more than one. - One repo, a strong model, names you mostly know. Grep is enough. - An agent that edits a lot by symbol. Serena. - You already run Milvus or Zilliz Cloud, or want to pick the embedding provider. claude-context. - Many repos, documents next to the code, nothing to sign up for. That's the case I built Semlith for. The full runs with every command are on semlith.com and the benchmark harness is in the repo at semlith/semlith. What are you using for code search with your agents right now, and where does it fall over?
🧠 چطور به AI کمک کنیم بدون خواندن کل مخزن GitHub، پروژه رو بهتر درک کنه؟ ابزار Serena یک MCP متنباز و کاربردیه که قابلیتهای یک IDE رو در اختیار Agentهای کدنویسی مثل Claude Code و Codex قرار میده. 🔗 لینک GitHub: oraios/serena چه کاری انجام میده؟ وقتی یک پروژه رو به Agent میدی، Serena بهش کمک میکنه ساختار کد رو بررسی کنه و بهجای خواندن بیهدف تمام فایلها، سراغ بخشهای مرتبط بره: - پیدا کردن توابع، کلاسها و متغیرها (Symbols) - شناسایی ارتباط بین بخشهای مختلف کد - پیدا کردن محل استفاده از هر تابع یا متغیر - بررسی وابستگیها و ساختار پروژه - ویرایش و بازنویسی کد با درک ساختار واقعی اون چرا مهمه؟ بهجای اینکه Agent کل مخزن رو یکجا وارد Context کنه، میتونه اطلاعات موردنیازش رو هدفمند پیدا کنه. این یعنی استفاده بهینهتر از Context و کاهش اطلاعات اضافی، بهخصوص در پروژههای بزرگ. Serena خودش مدل هوش مصنوعی نیست؛ از طریق MCP به ابزارهایی مثل Claude Code و Codex متصل میشه و امکانات تحلیل و ویرایش کد رو در اختیارشون قرار میده. 📌 اگر با مخزنهای بزرگ GitHub و ابزارهای کدنویسی AI کار میکنی، Serena ارزش امتحان کردن داره.
GPT-6 Astra 的自主循环太猛了！ 把一个 GitHub 仓库交给一个 Astra oraios/serena 一晚上过去，它趁你睡觉就把一天大约 5 小时的工作量干完了。 它先解析整个代码库， 只找出「Astra 现在真正该读的文件、符号和依赖关系」。 不让它一上来就把巨型仓库全读一遍。 光这一步就能省掉大量 Context 浪费。
📌 영상에 나온 도구 링크 모음입니다! 1. 포니테일 (Ponytail) DietrichGebert/ponytail 2. 케이브맨 (Caveman) JuliusBrussee/caveman 3. RTK rtk-ai/rtk 4. 헤드룸 (Headroom) headroomlabs-ai/headroom 5. 컨텍스트 모드 (Context Mode) mksglu/context-mode 6. 세레나 (Serena) oraios/serena 7. 토큰 옵티마이저 (Token Optimizer) alexgreensh/token-optimizer
개발자들이 먼저 깔았다..꼭 알아야 할 토큰 절약 도구 깃허브 TOP 7(깃허브 ★51만) AI 코딩할 때 토큰이 새는 네 군데(쓰는 양·읽는 양·찾아 헤맴·내 설정)와, 그걸 막으려고 개발자들이 만든 깃허브 도구 7개를 정리했습니다. 00:00 오프닝 00:28 포니테일 01:47 케이브맨 02:54 RTK 04:15 헤드룸 05:27 컨텍스트 모드 06:31 세레나 07:39 토큰 옵티마이저 08:39 마무리 📌 영상에 나온 도구 링크 1. 포니테일 (Ponytail) DietrichGebert/ponytail 2. 케이브맨 (Caveman) JuliusBrussee/caveman 3. RTK rtk-ai/rtk 4. 헤드룸 (Headroom) headroomlabs-ai/headroom 5. 컨텍스트 모드 (Context Mode) mksglu/context-mode 6. 세레나 (Serena) oraios/serena 7. 토큰 옵티마이저 (Token Optimizer) alexgreensh/token-optimizer [en-US] Developers' Must-Have Token Saving Tools: Top 7 GitHub Repos (517K Stars) I have summarized the four places where tokens leak when coding with AI (writing volume, reading volume, searching, and my settings), and seven GitHub tools created by developers to prevent them. I have compiled a list of these tools. 00:00 Opening 00:28 Ponytail 01:47 Caveman 02:54 RTK 04:15 Headroom 05:27 Context Mode 06:31 Serena 07:39 Token Optimizer 08:39 Wrap-up 📌 Links to tools featured in the video 1. Ponytail DietrichGebert/ponytail 2. Caveman JuliusBrussee/caveman 3. RTK rtk-ai/rtk 4. Headroom headroomlabs-ai/headroom 5. Context Mode mksglu/context-mode 6. Serena (Serena) oraios/serena 7. Token Optimizer alexgreensh/token-optimizer [id] Alat Penghemat Token Wajib Punya Pilihan Pengembang (Total 517 Ribu Bintang di GitHub) TOP 7 Saya telah merangkum empat tempat di mana token bocor saat melakukan pengkodean dengan AI (volume penulisan, volume pembacaan, pencarian, dan pengaturan saya), dan tujuh alat GitHub yang dibuat oleh pengembang untuk mencegahnya. Saya telah menyusun daftar alat-alat tersebut. 00:00 Pembukaan 00:28 Ponytail 01:47 Caveman 02:54 RTK 04:15 Headroom 05:27 Context Mode 06:31 Serena 07:39 Token Optimizer 08:39 Penutup 📌 Tautan ke alat yang ditampilkan dalam video 1. Ponytail DietrichGebert/ponytail 2. Caveman JuliusBrussee/caveman 3. RTK rtk-ai/rtk 4. Headroom headroomlabs-ai/headroom 5. Context Mode mksglu/context-mode 6. Serena (Serena) oraios/serena 7. Token Pengoptimal alexgreensh/token-optimizer
@goan999999 更新一下提示词： 请阅读 Serena 官方文档 oraios/serena 和 oraios.github.io 一节），然后： 1. 检查是否已安装 uv，没有则按官方方式安装 2. 用 `uv tool install -p 3.13 serena-agent` 安装，运行 `serena init` 验证 3. 优先用 `serena setup codex` 配置；如需手动，只在 ~/.codex/config.toml 里追加 [mcp_servers.serena] 段，保留现有所有 MCP 配置，修改前先备份原文件 4. 按官方文档配置 ~/.codex/hooks.json（activate / remind / reset / cleanup）； 如果已有 hooks.json，合并进去，不要覆盖 5. 不要使用 MCP 市场或旧的 uvx git 安装方式 6. 完成后告诉我改了哪些文件、怎么用 /mcp 验证 而且吧90%的节省量，估计就是博眼球的
@typecraft_dev I've been using serena oraios/serena for this among other things for some time
Serena: A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent (30k stars) What it does All text below is quoted directly from the project README. >Serena provides essential semantic code retrieval, editing, refactoring and debugging tools that are akin to an IDE's capabilities, operating at the symbol level and exploiting relational structure. Serena's agent-first tool design involves robust high-level abstractions, distinguishing it from approaches that rely on low-level concepts like line numbers or primitive search patterns. Practically, this means that your agent operates faster, more efficiently and more reliably, especially in larger and more complex codebases. While it is humans who download and set up Serena, our end users are essentially AI agents. As the ones actually applying Serena's tools, they are in the best position to evaluate Serena. Repository oraios/serena