| Репо | Issue | Заголовок | Наш актив (PR-порт) | Матч | Мерж (liveness) | Возраст | Флаги |
|---|---|---|---|---|---|---|---|
| microsoft/agent-framework | #7681 | .NET: [Feature]: Add persistence support for Agent Plan and Todo state | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ | L | HIGH | 10д | запрос контента |
| google/adk-python-community | #171 | feat(plugins): add AuthorityRoutingPlugin — pre-execution authority posture (ADVISE/EXECUTE/DEFER/STOP) | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | L | HIGH | 33д | запрос контентачужой PR |
| google/adk-python-community | #169 | feat(memory): add MongoDBMemoryService with Atlas Vector Search support | Persistent memory / second-brain (context resets) ↗ | L | HIGH | 36д | запрос контента |
| google/adk-python-community | #113 | Add SidClaw Governance Service integration | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ MCP tool trust / verification before execution ↗ | L | HIGH | 146д | запрос контентачужой PR |
| openai/openai-agents-js | #1097 | Feature: approve() with modified arguments | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | L | HIGH | 164д | запрос контентачужой PR |
| google/adk-python-community | #99 | feat(memory): add DatabaseMemoryService with SQL backend and agent scratchpad | Persistent memory / second-brain (context resets) ↗ | L | HIGH | 166д | запрос контента |
| google/adk-python-community | #69 | Feature Request: Add Milvus-backed Memory Service | Persistent memory / second-brain (context resets) ↗ | L | HIGH | 196д | запрос контента |
| google-gemini/cookbook | #1337 | Hybrid File Search + Google Search grounding example | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ | L | MED-HIGH | 5д | запрос контента |
| google-gemini/cookbook | #1345 | input_audio_transcription returns fabricated content in unspoken languages while the model understands the aud | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ | L | MED-HIGH | 0д | запрос контента |
| microsoft/semantic-kernel | #14312 | OpenAPI plugin SSRF validator: resolved IP is not pinned for the connection (DNS check-time vs use-time gap) | MCP tool trust / verification before execution ↗ | L | MED | 3д | запрос контентачужой PR |
| microsoft/semantic-kernel | #14302 | Feature Request: Native Token Metering & Bounded Overshoot (x402 Protocol) | Verified-ops SDK agent (verify before act) ↗ Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | L | MED | 7д | запрос контента |
| microsoft/semantic-kernel | #14295 | Python: relevance-score gates (min_relevance_score / DEFAULT_RELEVANCE) have no polarity cases in tests: a mem | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ Persistent memory / second-brain (context resets) ↗ Verified-ops SDK agent (verify before act) ↗ | L | MED | 8д | запрос контентачужой PR |
| openai/openai-cookbook | #2922 | [FEATURE] Recipe: gate research/agent output on proof-of-work (0 searches, 0 citations) before consuming it | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ Persistent memory / second-brain (context resets) ↗ | L | MED | 20д | запрос контента |
| microsoft/semantic-kernel | #14248 | [Feature Request]: Add Creduent zero-trust agent verification plugin to Semantic Kernel Python | MCP tool trust / verification before execution ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ Verified-ops SDK agent (verify before act) ↗ | L | MED | 23д | запрос контента |
| microsoft/semantic-kernel | #14240 | Python: server_url_validator allows Azure WireServer (168.63.129.16) and IPv6-embedded IPv4 forms (NAT64/6to4/ | MCP tool trust / verification before execution ↗ | L | MED | 27д | запрос контентачужой PR |
| microsoft/semantic-kernel | #14098 | .Net: Feature: Mimir as a Semantic Kernel memory connector (offline, encrypted, single-binary, cross-platform) | Persistent memory / second-brain (context resets) ↗ | L | MED | 67д | запрос контента |
| microsoft/semantic-kernel | #14072 | Python: Lack of Runtime Access Control (RBAC/Approval Mechanism) in Auto Function Invocation Leads to Unauthor | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ MCP tool trust / verification before execution ↗ | L | MED | 73д | запрос контента |
| GoogleCloudPlatform/generative-ai | #2904 | [Bug]: Computer use example has been updated to gemini-3.5-flash but the computer use tool does not support th | Computer-use / GUI agent ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | L | MED | 85д | запрос контента |
| meta-llama/PurpleLlama | #230 | Add AgentThreatBench to CyberSecEval: OWASP Agentic Top 10 benchmark (UK AISI) | Adversarial self-verification / burden-of-proof ↗ Persistent memory / second-brain (context resets) ↗ MCP tool trust / verification before execution ↗ | L | MED | 98д | запрос контентачужой PR |
| meta-llama/PurpleLlama | #231 | AgentThreatBench: OWASP Agentic Top 10 benchmark — complement to CyberSecEval for agentic threat scenarios | Persistent memory / second-brain (context resets) ↗ Adversarial self-verification / burden-of-proof ↗ MCP tool trust / verification before execution ↗ | L | MED | 98д | запрос контента |
| meta-llama/PurpleLlama | #147 | How to combine PromptGuard-2 and AlignmentCheck? | Adversarial self-verification / burden-of-proof ↗ MCP tool trust / verification before execution ↗ | L | MED | 268д | запрос контента |
| GoogleCloudPlatform/generative-ai | #2272 | [Bug]: MemoryBank with Crewai example not working | Persistent memory / second-brain (context resets) ↗ | L | MED | 370д | запрос контента |
| GoogleCloudPlatform/generative-ai | #2046 | [Bug]: discoveryengine.SearchRequest can't find results | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ | L | MED | 471д | запрос контента |
| GoogleCloudPlatform/generative-ai | #1204 | [Bug]: evaluate_gemini_with_autosxs: my computer SvcAcct doesnt have access to my bucket. | Verified-ops SDK agent (verify before act) ↗ Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | L | MED | 692д | запрос контента |
| microsoft/agent-framework | #7841 | Python: MCPStreamableHTTPTool.connect() never sends a header_provider's headers, so any headers_env/header_pro | MCP tool trust / verification before execution ↗ | M | HIGH | 1д | запрос контента |
| microsoft/agent-framework | #7836 | Python: [Bug]: Gemini chat client drops unmapped finish reasons and their usage/token accounting | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 1д | запрос контентачужой PR |
| microsoft/agent-framework | #7834 | .NET: Proposal: Integrating Foundgine as a Semantic Execution Layer for AI Agents | Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 2д | запрос контента |
| microsoft/agent-framework | #7831 | Python: [Bug]: get_latest returns a stale checkpoint when the newest one cannot be decoded | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ Verified-ops SDK agent (verify before act) ↗ | M | HIGH | 2д | запрос контентачужой PR |
| microsoft/agent-framework | #7825 | .NET: [Bug]: Hosted MCP calls remain sequential despite parallel_tool_calls=true | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ MCP tool trust / verification before execution ↗ | M | HIGH | 2д | запрос контента |
| microsoft/agent-framework | #7824 | .NET: [Feature]: Support MCP 2026-07-28 specification (including Tasks Extension) in Agent Framework .NET MCP | MCP tool trust / verification before execution ↗ | M | HIGH | 2д | запрос контента |
| microsoft/agent-framework | #7822 | Bug: Multimodal content is dropped during agent handoff in orchestrator | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 3д | запрос контентачужой PR |
| microsoft/agent-framework | #7810 | Python: Python AG-UI Magentic TEXT_MESSAGE_END emmitted after RUN_FINISHED when plan review is enabled and re | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 4д | запрос контента |
| microsoft/agent-framework | #7811 | .NET: [Bug]: AGUIChatClient client-tool loop duplicates persisted messages with MapAGUIServer + AgentSessionSt | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 4д | запрос контента |
| microsoft/agent-framework | #7805 | .NET: [Feature]: Please add example to store conversation in database (.NET API Hosting) | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 4д | запрос контента |
| microsoft/agent-framework | #7802 | Python: [Feature]: Compose AG-UI snapshots with HistoryProvider, pagination, and compaction | Persistent memory / second-brain (context resets) ↗ Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 4д | запрос контента |
| microsoft/agent-framework | #7796 | .NET: Defer checkpoint cleanup until workflow restoration succeeds | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 5д | запрос контента |
| microsoft/agent-framework | #7789 | Python: Built-in group chat message types are rejected during checkpoint restore | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 5д | запрос контентачужой PR |
| microsoft/agent-framework | #7763 | .NET: Preserve nested executor identity in workflow lifecycle events | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 6д | запрос контентачужой PR |
| microsoft/agent-framework | #7767 | Python: [Bug]: Streaming Agent telemetry fails across FastAPI/Azure Functions response context | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 6д | запрос контента |
| microsoft/agent-framework | #7771 | Python: [Bug]: python/README.md still says "Learn docs are coming soon" | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 6д | запрос контентачужой PR |
| google/adk-python-community | #177 | Proposal: fail-closed AgentFuse gate in `before_tool_callback` | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ | M | HIGH | 7д | запрос контента |
| microsoft/agent-framework | #7710 | Python: AG-UI snapshot replay with service sessions blocks Foundry Hosted Agents | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ | M | HIGH | 7д | запрос контентачужой PR |
| microsoft/agent-framework | #7707 | Python: python AG-UI : workflow.as_Agent + AgentFrameworkAgent resume return expected Content, got str | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 7д | запрос контентачужой PR |
| microsoft/agent-framework | #7694 | .NET: [Bug]: StreamingRun.WatchStreamAsync() can silently stop yielding events after a long-running executor t | Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ Verified-ops SDK agent (verify before act) ↗ | M | HIGH | 8д | запрос контента |
| microsoft/agent-framework | #7643 | [Feature]: Support `ask_user` tool | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 12д | запрос контента |
| microsoft/agent-framework | #7538 | Python: [Bug]: Background Responses tool loop fails when chaining tool output to a completed background respon | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 19д | запрос контента |
| microsoft/agent-framework | #7384 | .NET: [Bug]: AgentWorkflowBuilder Handoff orchestration breaks when handoffs bounce back, especially with reas | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 27д | запрос контента |
| microsoft/agent-framework | #7358 | .NET: Update compaction docs to show different ways to use a Compaction Strategy with their implications | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 28д | запрос контента |
| microsoft/agent-framework | #7215 | Python: [Feature]: persist AG-UI thread snapshots incrementally (and handle client disconnect), not only at ru | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 36д | запрос контента |
| microsoft/agent-framework | #6909 | .NET: Python: [Bug]: AG-UI appends approval-resolved tool results out of order — invalid history for strict ch | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ MCP tool trust / verification before execution ↗ | M | HIGH | 53д | запрос контента |
| google/adk-python-community | #155 | feat: Add ValkeyMemoryService with vector similarity search (Valkey Search module) | Adversarial self-verification / burden-of-proof ↗ Persistent memory / second-brain (context resets) ↗ | M | HIGH | 82д | запрос контентачужой PR |
| openai/openai-agents-js | #1353 | Firefox WebRTC Realtime sessions disconnect mid-turn; likely ICE consent / USE-CANDIDATE interop | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 96д | запрос контента |
| google/adk-python-community | #142 | feat: post-execution audit trail pattern to complement AgentGovernancePlugin | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 97д | запрос контента |
| google/adk-python-community | #129 | [Community Project] create-google-adk-agent — one-command scaffold for ADK projects | Pipeline-vs-barrier concurrency (замер 1.93×) ↗ Multi-agent consensus / voting ↗ Persistent memory / second-brain (context resets) ↗ MCP tool trust / verification before execution ↗ | M | HIGH | 110д | |
| microsoft/agent-framework | #5621 | .NET: [Bug]: Checkpointing in Handoff Workflow | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 113д | запрос контента |
| google/adk-python-community | #103 | feat: add FirestoreSessionService for serverless session persistence | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 157д | запрос контента |
| google/adk-python-community | #97 | Integration Proposal: SDC Agents — Deterministic Semantic Data Artifacts from Enterprise Datastores | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 167д | запрос контента |
| google/adk-python-community | #91 | feat: Add LangExtract tool for structured information extraction | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ | M | HIGH | 187д | запрос контентачужой PR |
| google/adk-python-community | #88 | feat(plugins): add fallback plugin to automatically fallback between Gemini models | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 188д | запрос контента |
| google/adk-python-community | #46 | Add self-hosted option to manage working memory (sessions) longterm memory management with ADK | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 210д | чужой PR |
| google/adk-python-community | #7 | feat: add Typesense-based session service | Persistent memory / second-brain (context resets) ↗ | M | HIGH | 309д | запрос контента |
| openai/openai-agents-js | #585 | Realtime Agent Using `function_call` Instead of `mcp_call` for Hosted MCP Tools | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ MCP tool trust / verification before execution ↗ | M | HIGH | 313д | запрос контента |
| google/adk-python-community | #21 | First-class Temporal integration for Google ADK | Multi-agent consensus / voting ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 354д | запрос контента |
| huggingface/cookbook | #325 | Invalid Notebooks | Citation-faithfulness eval (hallucinated/unsupported citations) ↗ | M | HIGH | 355д | запрос контента |
| huggingface/cookbook | #316 | Execution Error in Agents recipes | Multi-agent consensus / voting ↗ | M | HIGH | 401д | запрос контента |
| huggingface/cookbook | #303 | Contribution to Hugging Face 🤗 cookbook: Add a search agent cookbook | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 451д | запрос контентачужой PR |
| huggingface/cookbook | #90 | ValidationError: 1 validation error for agenerate | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 840д | запрос контента |
| openai/openai-agents-python | #4665 | Docs/example: server-wide tool guardrails for MCP servers | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ MCP tool trust / verification before execution ↗ | M | HIGH | 0д | запрос контента |
| openai/openai-agents-python | #4646 | NextStepInterruption bypasses resumed Session-write recovery and loses tool guardrail results | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ Pipeline-vs-barrier concurrency (замер 1.93×) ↗ | M | HIGH | 0д | запрос контентачужой PR |
| microsoft/agent-framework | #7862 | .NET: [Bug]: MAF approval-required function call is persisted as a dangling FunctionCallContent and pending ap | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Verified-ops SDK agent (verify before act) ↗ | M | HIGH | 0д | запрос контентачужой PR |
| microsoft/agent-framework | #7857 | .NET: [Bug]: ToolApprovalRequestContent triggers 2 times in handoff workflow with different Id's | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 0д | запрос контента |
| microsoft/agent-framework | #7853 | .NET: [Feature]: provide an official sandbox abstraction for command/tool execution | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ | M | HIGH | 0д | запрос контента |
| microsoft/agent-framework | #7852 | .NET: [Feature]: first-class request/interaction context for dynamic model and tool policy | Authority routing ADVISE / EXECUTE / DEFER / STOP ↗ Persistent memory / second-brain (context resets) ↗ | M | HIGH | 0д | запрос контента |
| google-gemini/cookbook | #1328 | `gemini-3.1-flash-live-preview`: a 1.0 s mid-sentence pause closes the turn while the caller is still speaking | Adversarial self-verification / burden-of-proof ↗ | M | MED-HIGH | 7д | запрос контента |
| Issue | Заголовок | Наш матч | Возраст | Обновл. | 💬 | Флаги |
|---|---|---|---|---|---|---|
| #325 | Invalid Notebooks | citation-faithfulness | 355д | 355д | 0 | |
| #316 | Execution Error in Agents recipes | consensus | 401д | 401д | 0 | |
| #303 | Contribution to Hugging Face 🤗 cookbook: Add a search agent cookbook | authority-routing | 451д | 32д | 4 | чужой PR |
| #90 | ValidationError: 1 validation error for agenerate | authority-routing, pipeline-barrier | 840д | 840д | 0 | |
| #363 | "Post training a VLM for reasoning with GRPO using TRL" Not Work | 44д | 44д | 0 | ||
| #339 | Add Quantum Circuit Optimization with Qiskit and VQE Notebook | 255д | 255д | 0 | ||
| #337 | 404 on https://api-inference.huggingface.co/models/bigcode/starcoder | 295д | 295д | 0 | ||
| #328 | An Error In "Fine-Tuning a Vision Language Model (Qwen2-VL-7B) with the Hugging Face Ecosystem (TRL)" Notebook | 346д | 346д | 0 | ||
| #326 | Improve the Knowledge Graphs cookbook | 350д | 350д | 1 | ||
| #322 | "Building RAG with Custom Unstructured Data" - SimpleLocalConfig | 387д | 387д | 0 | ||
| #313 | 🧑🍳 New Cookbook Recipe: Add a recipe showcasing the usage of Pruna with Diffusers | 406д | 405д | 4 | ||
| #310 | Invalid Notebooks | 414д | 414д | 0 | чужой PR | |
| #301 | Bring Arabic to the Hugging Face Cookbook! | 452д | 452д | 1 | ||
| #292 | Non generic example causes. Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() ins | 520д | 520д | 0 | ||
| #291 | mongodb_smolagents_multi_micro_agents.ipynb | 531д | 531д | 1 | ||
| #268 | Reusing index with from_index() caused "No passages provided" | 596д | 596д | 0 | ||
| #216 | Turkish translations | 673д | 50д | 14 | мейнт | |
| #185 | Weird redirection in URL in `Advanced RAG on Hugging Face documentation using LangChain` cookbook | 725д | 725д | 0 | мейнт | |
| #183 | "RAG with unstructured data", uses `documents` instead of `docs` / unused `docs` variable? | 730д | 730д | 0 | ||
| #181 | Incorrect links to the source files | 733д | 733д | 0 | ||
| #92 | Translate to Russian (RU) | 837д | 836д | 0 | ||
| #83 | Quantization Stable Diffusion | 852д | 852д | 0 | чужой PR | |
| #82 | Call for Contributions | 853д | 742д | 15 | мейнт | |
| #72 | Structured Text-to-SQL generation using Hugging Face and Outlines | 873д | 124д | 2 | ||
| #65 | Train | 885д | 883д | 2 | ||
| #57 | RAG: Question Answering using Gemma, Elasticsearch & langchain | 903д | 883д | 1 | ||
| #48 | Some outputs of code cells don't show up on hf.co/learn | 910д | 421д | 1 | ||
| #43 | Comprehensive Cookbook for Fine-tuning Gemma Model on Mental Health Assistant Dataset | 915д | 910д | 4 | ||
| #39 | Contribution to Hugging Face 🤗 cookbook: Add a LangChain agent that can interact with a graph database | 918д | 917д | 1 | ||
| #34 | Translate to Simplified Chinese (zh-CN) | 919д | 630д | 4 | ||
| #25 | Idea for contribution : Recipe on Training FineTuning Embeddings / Re-Rankers on Custom Domain Specific Datase | 921д | 921д | 2 |