traceloop/openllmetry
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Is traceloop/openllmetry beginner-friendly?
In the last 30 days, traceloop/openllmetry merged 1 of 53 pull requests from outside contributors, and its maintainers usually reply within 1 day. 26 beginner-friendly issues are open now.
- Stars
- 7.5k
- Forks
- 1.2k
- Open beginner issues
- 26
- Indexed issues
- 184
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 2
- Dominant language
- Python
- License
- Apache-2.0
- Last GitHub push
- Nov 5, 2026
- Latest indexed
- Sep 19, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- help wanted good first issue
How to contribute to traceloop/openllmetry
- Read the contributing guide first: it says how the maintainers want changes proposed, tested and reviewed.
- Read its code of conduct: it covers issues and pull requests as well as chat.
- Your contributions will be published under the project's Apache-2.0 license.
- Pick one of the 26 open beginner-friendly issues below and comment that you want to work on it before you start.
Issues somebody may already be working on are listed last. List everything by date
-
bug python
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
traceloop/openllmetry#4717 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
traceloop/openllmetry#4716 ·
Maintainers usually reply within 1 day
-
🚀 Feature: Support for deepagentsMay be free again @Saksham-chourasia claimed this 43 days ago, and no pull request is open. Open
Difficulty 5/5 Over a week Newbie friendliness 38/100
traceloop/openllmetry#4550 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
traceloop/openllmetry#4404 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
traceloop/openllmetry#4347 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 30/100
traceloop/openllmetry#4340 · 6 comments ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 45/100
traceloop/openllmetry#4291 · 3 comments ·
Maintainers usually reply within 1 day
-
🚀 Feature: Ollama instrumentation missing inference metadata attributes in spansMay be free again @krishna231122-del claimed this 157 days ago, and no pull request is open. Open
Difficulty 3/5 1-2 days Newbie friendliness 68/100
traceloop/openllmetry#4192 · 3 comments ·
Maintainers usually reply within 1 day
-
🚀 Feature: langchain 1.0+ supportMay be free again @anuj342 claimed this 239 days ago, and no pull request is open. Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
traceloop/openllmetry#3834 · 3 comments ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
traceloop/openllmetry#3257 · 4 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: httpx and other instrumentations are not playing well with langchain instrumentationOpen
Difficulty 4/5 3-5 days Newbie friendliness 42/100
traceloop/openllmetry#3214 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
traceloop/openllmetry#3200 · 6 comments · 2 reactions ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
traceloop/openllmetry#3167 · 8 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Gemini streaming raises TypeError after the last chunk when usage metadata has no candidates_token_countPossibly taken @prassu017 claimed this 1 day ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
traceloop/openllmetry#4711 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: gen_ai.client.operation.duration lost its histogram view in #3129, falls back to default ms bucketsPossibly taken @mccalpink claimed this 6 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 25/100
traceloop/openllmetry#4702 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Anthropic: since anthropic 1.14.0 each call reports its usage on two spansPossibly taken @simin-yuan claimed this 6 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 56/100
traceloop/openllmetry#4700 · 4 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT is ignored, only TRACELOOP_TRACE_CONTENT disables content capturePossibly taken @yuee3 claimed this 14 days ago. Openbug python
Difficulty 4/5 3-5 days Newbie friendliness 45/100
traceloop/openllmetry#4691 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.input.messages on image requests when no uploader is configuredPossibly taken @Tyagiquamar claimed this 14 days ago. Openbug python
Difficulty 2/5 1-3 hours Newbie friendliness 35/100
traceloop/openllmetry#4690 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: opentelemetry-instrument silently skips langchain, llamaindex, writer and watsonx (wrong instruments extra)Possibly taken @abhigyanpal1 claimed this 6 days ago. Openbug python
Difficulty 4/5 3-5 days Newbie friendliness 48/100
traceloop/openllmetry#4689 · 2 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: @task/@workflow input/output serialization errors other than TypeError escape into the decorated functionPossibly taken @caiotheodoro claimed this 15 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 35/100
traceloop/openllmetry#4686 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: MCP client tool span omits content blocks after the firstPossibly taken @CJstate claimed this 16 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 42/100
traceloop/openllmetry#4682 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Duplicate invoke_agent spans emitted for a single LangGraph invocationPossibly taken @CJstate claimed this 17 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 62/100
traceloop/openllmetry#4678 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Incomplete cache token migration after #4243 breaks Bedrock and Groq instrumentationPossibly taken @Quantum-Enigma-dot claimed this 21 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
traceloop/openllmetry#4665 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.reasoning_tokens on streamed chat completionsPossibly taken @jayfeng7 claimed this 23 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
traceloop/openllmetry#4660 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Qdrant async spans end before the operation runsPossibly taken @GaliFFun claimed this 24 days ago. Open
Difficulty 4/5 1-2 days Newbie friendliness 25/100
traceloop/openllmetry#4658 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: MCP uninstrument() keeps tracing and reinstrumentation duplicates spansPossibly taken @harshb16 claimed this 27 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 76/100
traceloop/openllmetry#4653 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Anthropic: a sync stream that fails mid-way never ends its spanPossibly taken @lakshya-dhariwal claimed this 30 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
traceloop/openllmetry#4643 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: LangChain: two LangGraph sessions read interleaved end up in one trace; an abandoned async session pulls the next session into its tracePossibly taken @lakshya-dhariwal claimed this 31 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 20/100
traceloop/openllmetry#4637 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: LangChain: TraceloopCallbackHandler raises AttributeError at every LangGraph interrupt() and resumePossibly taken @lakshya-dhariwal claimed this 31 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
traceloop/openllmetry#4636 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI Agents: with two concurrent runs of the same agent, a handoff span is recorded in the other run's tracePossibly taken @rupak-eng claimed this 31 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 30/100
traceloop/openllmetry#4635 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI Agents: uninstrument() leaves runs traced, and instrument() again records every span twicePossibly taken @anishgurjar claimed this 28 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 56/100
traceloop/openllmetry#4634 · 3 comments ·
Maintainers usually reply within 1 day
-
Bug Report: Failed dataset deletes still remove local rows and columnsPossibly taken @inchang-ing claimed this 32 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
traceloop/openllmetry#4630 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Langchain instrumentation adds empty create_agent graph nodes for every middleware hookPossibly taken @DEVJHAWAR11 claimed this 33 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 58/100
traceloop/openllmetry#4628 · 4 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Anthropic: after uninstrument(), a client that used with_raw_response / with_streaming_response stays traced through themPossibly taken @ningyixi claimed this 35 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 62/100
traceloop/openllmetry#4619 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: MCP instrumentation breaks fastmcp-slim client-only importsPossibly taken @wangjiawei-vegetable claimed this 38 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 20/100
traceloop/openllmetry#4612 · 3 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: openai-agents records every model call as two LLM spans (calls and tokens doubled)Possibly taken @Jennycruzy claimed this 38 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
traceloop/openllmetry#4609 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: llama streams: close() before reading never ends the span; aclose() leaves the HTTP response (connection) openPossibly taken @Suddha-Abhitej claimed this 37 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 68/100
traceloop/openllmetry#4608 · 4 comments ·
Maintainers usually reply within 1 day
-
Add delegation and pre-action authorization attributes for agent spansPossibly taken @Rutvij97 claimed this 9 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 38/100
traceloop/openllmetry#4599 · 5 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: LiteLLM instrumentation does not record seed, stop, frequency_penalty, presence_penaltyPossibly taken @shantam77 claimed this 38 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
traceloop/openllmetry#4598 · 2 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: LiteLLM instrumentation never ends the span when a call is interrupted (KeyboardInterrupt, asyncio cancellation)Possibly taken @rupak-eng claimed this 39 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 80/100
traceloop/openllmetry#4597 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Google GenAI instrumentation records no gen_ai.input.messages when contents is a tuplePossibly taken @jipeng6036-del claimed this 40 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 80/100
traceloop/openllmetry#4591 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: failed calls are missing from gen_ai.client.operation.duration or recorded without error.type (Google GenAI, Bedrock, Anthropic, OpenAI streams, LiteLLM)Possibly taken @CodeAlex52 claimed this 26 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 50/100
traceloop/openllmetry#4590 · 3 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Traces go missing when a model reports 0 tokensPossibly taken @manojmulammagari claimed this 37 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 62/100
traceloop/openllmetry#4588 · 2 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI Responses API records no metrics (gen_ai.client.operation.duration, gen_ai.client.token.usage)Possibly taken @zhaoruizhe81 claimed this 39 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 70/100
traceloop/openllmetry#4585 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.cache_read.input_tokens when usage.prompt_tokens_details is NonePossibly taken @rupak-eng claimed this 41 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
traceloop/openllmetry#4583 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Bedrock instrumentation: uninstrument() does not remove tracing from clients created while instrumentedPossibly taken @Aftabbs claimed this 43 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 68/100
traceloop/openllmetry#4577 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: openai, anthropic, google-generativeai: a call cancelled while waiting for the response (asyncio timeout/cancel, Ctrl-C) never ends its spanPossibly taken @chengwudi1 claimed this 41 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 58/100
traceloop/openllmetry#4576 · 2 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: MCP instrumentation crashes on error results with non-text contentPossibly taken @notshriyansh claimed this 43 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 73/100
traceloop/openllmetry#4569 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Bedrock invoke_model_with_response_stream records streamed tool-call arguments as {} (input_json_delta appended to the dict placeholder, error swallowed)Possibly taken @sanjana658 claimed this 45 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 25/100
traceloop/openllmetry#4558 · 2 comments ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Bedrock instrumentation does not record top_k / stop_sequences, and records no request parameters at all when the call failsPossibly taken @aniketkrs claimed this 45 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 20/100
traceloop/openllmetry#4557 · 1 comment ·
Maintainers usually reply within 1 day
Showing the newest 100
This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.