agentdryrun good first issues (Python)

Try mcp-record with a real MCP client (Claude Desktop, Cursor, VS Code) and report about 21 hours ago

help wanted good first issue

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

scan: more shells and tools (fish, nushell, make targets, python -c shutil.rmtree) 1 day ago

help wanted

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Run scan on your own history and tell us where the starter rules are wrong 1 day ago

help wanted

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

scan: read Codex CLI sessions (needs a redacted sample) 1 day ago

help wanted good first issue

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Translate the README and the quick start 1 day ago

help wanted good first issue docs

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Cross-check checkpoint and cosignature/v1 bytes against another implementation 1 day ago

help wanted verifier

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

A second verifier in Go (or Rust / JavaScript), from the spec alone 1 day ago

help wanted verifier

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Importer: OpenInference / Arize Phoenix tool spans 1 day ago

help wanted importer

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Real exports wanted: Langfuse, LangSmith, OpenTelemetry (redacted samples) 1 day ago

help wanted importer

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Importer: raw OpenAI and Anthropic tool-call logs 1 day ago

help wanted good first issue importer

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

Example rules for other workflows (refunds, data deletion, outbound email) 1 day ago

help wanted good first issue docs

ntinosgkiou-code/agentdryrun

0

A dry run for AI agents: record their tool calls, see what your rules would have blocked or sent for approval, and keep a tamper-evident record. Local, zero dependencies, Apache-2.0.

Python

#agentic-ai#ai-agent-security#ai-agents#ai-governance#ai-safety#audit-trail#dry-run#genai#guardrails#langfuse#langsmith#llm-observability#llmops#open-source#opentelemetry#python#security#tamper-evident#tool-calling

ntinosgkiou-code/agentdryrun

Open Issues Need Help