release: v2.1.0 — multi-language SDK readiness + TypeScript parity

Bump all packages to 2.1.0, TypeScript SDK to 1.0.0.
See RELEASE_NOTES_v2.1.0.md and CHANGELOG.md for full details.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: imran-siddique

CHANGELOG.md

@@ -7,12 +7,76 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.1.0] - 2026-03-15
+
+### 🚀 Highlights
+
+**Multi-language SDK readiness, TypeScript full parity, .NET NuGet hardening, 70+ commits since v1.1.0.** This release makes the toolkit a true polyglot governance layer — Python, TypeScript, and .NET are all first-class citizens with install instructions, quickstarts, and package metadata ready for registry publishing.
+
+### Added
+
+- **TypeScript SDK full parity** (— PolicyEngine + AgentIdentity) — rich policy evaluation with 4 conflict resolution strategies, expression evaluator, rate limiting, YAML/JSON policy documents, Ed25519 identity with lifecycle/delegation/JWK/JWKS/DID export, IdentityRegistry with cascade revocation. 136 tests passing. (#269)
+- **@agentmesh/sdk 1.0.0** — TypeScript package now publish-ready with `exports` field, `prepublishOnly` build hook, correct `repository.directory`, MIT license.
+- **Multi-language README** — root README now surfaces Python (PyPI), TypeScript (npm), and .NET (NuGet) install sections, badges, quickstart code, and a multi-SDK packages table.
+- **Multi-language QUICKSTART** — getting started guide now covers all three SDKs with code examples.
+- **Semantic Kernel + Azure AI Foundry** added to framework integration table.
+- **5 standalone framework quickstarts** — one-file runnable examples for LangChain, CrewAI, AutoGen, OpenAI Agents, Google ADK.
+- **Competitive comparison page** — vs NeMo Guardrails, Guardrails AI, LiteLLM, Portkey (`docs/COMPARISON.md`).
+- **GitHub Copilot Extension** — agent governance code review extension for Copilot.
+- **Observability integrations** — Prometheus, OpenTelemetry, PagerDuty, Grafana (#49).
+- **NIST RFI mapping** — question-by-question mapping to NIST AI Agent Security RFI 2026-00206 (#29).
+- **Performance benchmarks** — published BENCHMARKS.md with p50/p99 latency, throughput at 50 concurrent agents (#231).
+- **6 comprehensive governance tutorials** — policy engine, trust & identity, framework integrations, audit & compliance, agent reliability, execution sandboxing (#187).
+- **Azure deployment guides** — AKS, Azure AI Foundry, Container Apps, OpenClaw sidecar.
+
 ### Changed
 
-- **agent-governance** (formerly `ai-agent-compliance`): Renamed PyPI package from `ai-agent-compliance`
-  to `agent-governance` for better discoverability with the intended audience (platform engineers,
-  security architects). The old name is deprecated and will redirect for 6 months.
-  CLI gains `agent-governance` entry point; `agent-compliance` is retained as a backward-compatible alias.
+- **agent-governance** (formerly `ai-agent-compliance`): Renamed PyPI package for better discoverability.
+- **README architecture disclaimer** reframed from apology to confidence — leads with enforcement model, composes with container isolation (#240).
+- **README tagline** updated for OWASP 10/10 discoverability.
+- **.NET NuGet metadata** enhanced — Authors, License, RepositoryUrl, Tags, ReadmeFile in csproj.
+- All example install strings updated from `ai-agent-compliance[full]` to `agent-governance[full]`.
+- Demo fixed: legacy `agent-hypervisor` path → `agent-runtime`.
+- BENCHMARKS.md: fixed stale "VADP version" reference.
+
+### Fixed
+
+- **CostGuard input validation** — NaN/Inf/negative guards on all budget parameters, `_org_killed` flag prevents bypass after org threshold breach (#272).
+- **CostGuard thread safety** — bound breach history + Lock for concurrent access (#253).
+- **.NET bug sweep** — thread safety, error surfacing, caching, disposal fixes (#252).
+- **Behavioral anomaly detection** implemented in RingBreachDetector.
+- **ErrorBudget._events** bounded with `deque(maxlen=N)` (#172).
+- **VectorClock thread safety** + integrity type hints (#243).
+- **CLI edge case tests** and input validation for agent-compliance (#234).
+- **Cross-package import errors** breaking CI resolved (#222).
+- **OWASP-COMPLIANCE.md** broken link fix + Copilot extension server hardening (#270).
+
+### Security
+
+- Block `importlib` dynamic imports in sandbox (#189).
+- Centralize hardcoded ring thresholds and constants (#188).
+
+### Infrastructure
+
+- Phase 3 architecture rename propagated across 52 files (#221).
+- Deferred architecture extractions — slim OS init, marketplace, lightning (#207).
+- Architecture naming review and layer consolidation (#206).
+- agentmesh-integrations migrated into monorepo (#138).
+- CI test matrix updated with agentmesh-integrations packages (#226).
+- OpenSSF Scorecard improved from 5.3 to ~7.7 (#113, #137).
+
+### Install
+
+```bash
+# Python
+pip install agent-governance[full]
+
+# TypeScript
+npm install @agentmesh/sdk
+
+# .NET
+dotnet add package Microsoft.AgentGovernance
+```
 
 ## [2.0.2] - 2026-03-12
 
@@ -162,6 +226,7 @@ pip install agent-governance[full]
 - Pinned all Docker base images by SHA256 digest.
 - Removed `gradle-wrapper.jar` binary artifact.
 
+[2.1.0]: https://github.com/microsoft/agent-governance-toolkit/releases/tag/v2.1.0
 [1.1.0]: https://github.com/microsoft/agent-governance-toolkit/releases/tag/v1.1.0
 [1.0.1]: https://github.com/microsoft/agent-governance-toolkit/releases/tag/v1.0.1
 [1.0.0]: https://github.com/microsoft/agent-governance-toolkit/releases/tag/v1.0.0

RELEASE_NOTES_v2.1.0.md

@@ -0,0 +1,119 @@
+# Agent Governance Toolkit v2.1.0
+
+**The missing security layer for AI agents — now in Python, TypeScript, and .NET.**
+
+Runtime policy enforcement, zero-trust identity, execution sandboxing, and SRE — 10/10 OWASP Agentic Top 10 coverage with 6,100+ tests across three languages.
+
+## 🚀 What's New
+
+### Multi-Language SDK Readiness
+
+The toolkit is now a **polyglot governance layer**. All three SDKs have first-class install instructions, quickstart code, and package metadata ready for registry publishing.
+
+| Language | Package | Install |
+|----------|---------|---------|
+| **Python** | [`agent-governance[full]`](https://pypi.org/project/agent-governance/) | `pip install agent-governance[full]` |
+| **TypeScript** | [`@agentmesh/sdk`](https://www.npmjs.com/package/@agentmesh/sdk) | `npm install @agentmesh/sdk` |
+| **.NET** | [`Microsoft.AgentGovernance`](https://www.nuget.org/packages/Microsoft.AgentGovernance) | `dotnet add package Microsoft.AgentGovernance` |
+
+### TypeScript SDK Full Parity (1.0.0)
+
+The TypeScript SDK now has full feature parity with the Python PolicyEngine and AgentIdentity:
+
+- **PolicyEngine** — rich policy evaluation with 4 conflict resolution strategies, expression evaluator (equality, inequality, numeric, in/not-in, boolean, and/or, nested paths), rate limiting, YAML/JSON policy document loading
+- **AgentIdentity** — Ed25519 cryptographic identity with lifecycle management (active/suspended/revoked), capability wildcards, delegation chains, JWK/JWKS import/export, W3C DID Document export
+- **IdentityRegistry** — agent registry with cascade revocation
+- **PolicyConflictResolver** — 4 strategies: deny-overrides, allow-overrides, priority-first-match, most-specific-wins
+- **136 tests** passing (57 existing + 79 new parity tests)
+
+### .NET SDK Hardened for NuGet
+
+Enhanced NuGet package metadata — authors, license, repository URL, package tags, and readme now included in the `.csproj`. The .NET SDK covers all 10 OWASP Agentic risks with policy enforcement, execution rings, saga orchestration, circuit breakers, SLO tracking, prompt injection detection, and OpenTelemetry metrics.
+
+### Framework Integrations Expanded
+
+Now supports **13+ agent frameworks** including new entries:
+
+- **Semantic Kernel** — Native (.NET + Python) integration
+- **Azure AI Foundry** — Deployment guide for agent governance in Foundry Agent Service
+
+Plus existing integrations: Microsoft Agent Framework, LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Google ADK, Dify, LlamaIndex, Haystack.
+
+### Performance Benchmarks Published
+
+| Metric | Latency (p50) | Throughput |
+|---|---|---|
+| Policy evaluation (1 rule) | 0.012 ms | 72K ops/sec |
+| Policy evaluation (100 rules) | 0.029 ms | 31K ops/sec |
+| Kernel enforcement | 0.091 ms | 9.3K ops/sec |
+| Concurrent throughput (50 agents) | — | 35,481 ops/sec |
+
+Full methodology: [BENCHMARKS.md](BENCHMARKS.md)
+
+## Key Changes Since v1.1.0
+
+### Added
+- TypeScript SDK full parity — PolicyEngine + Identity + 136 tests (#269)
+- 5 standalone framework quickstarts — LangChain, CrewAI, AutoGen, OpenAI Agents, Google ADK
+- Competitive comparison page — vs NeMo Guardrails, Guardrails AI, LiteLLM, Portkey
+- GitHub Copilot Extension for agent governance code review
+- Observability integrations — Prometheus, OTel, PagerDuty, Grafana (#49)
+- NIST RFI mapping — NIST AI Agent Security RFI 2026-00206 (#29)
+- 6 comprehensive governance tutorials (#187)
+- Azure deployment guides — AKS, AI Foundry, Container Apps, OpenClaw
+
+### Fixed
+- CostGuard input validation + org kill bypass prevention (#272)
+- CostGuard thread safety — bound breach history + Lock (#253)
+- .NET bug sweep — thread safety, error surfacing, caching, disposal (#252)
+- Behavioral anomaly detection in RingBreachDetector
+- ErrorBudget._events bounded with deque (#172)
+- VectorClock thread safety (#243)
+- Cross-package import errors (#222)
+- OWASP-COMPLIANCE.md broken link (#270)
+
+### Infrastructure
+- Architecture rename propagated across 52 files (#221)
+- OpenSSF Scorecard improved to ~7.7 (#113, #137)
+- agentmesh-integrations migrated into monorepo (#138)
+- Phase 2 + Phase 3 architecture consolidation (#206, #207)
+
+## Security & Compliance
+
+| Framework | Coverage |
+|-----------|----------|
+| OWASP Agentic Top 10 (2026) | 10/10 risks |
+| CSA Agentic Trust Framework | 15/15 requirements |
+| NIST AI RMF | Govern, Map, Measure, Manage |
+| EU AI Act | Risk classification, audit trails, human oversight |
+
+## Quick Start
+
+```bash
+# Python
+pip install agent-governance[full]
+
+# TypeScript
+npm install @agentmesh/sdk
+
+# .NET
+dotnet add package Microsoft.AgentGovernance
+```
+
+```python
+from agent_os import PolicyEngine, CapabilityModel
+
+engine = PolicyEngine(capabilities=CapabilityModel(
+    allowed_tools=["web_search", "file_read"],
+    denied_tools=["file_write", "shell_exec"],
+))
+decision = engine.evaluate(agent_id="researcher-1", action="tool_call", tool="web_search")
+```
+
+## Full Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for the complete list of changes.
+
+## License
+
+[MIT](LICENSE) — © Microsoft Corporation

packages/agent-compliance/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-governance"
-version = "1.1.0"
+version = "2.1.0"
 description = "Unified installer and runtime policy enforcement for the Agent Governance Toolkit"
 readme = "README.md"
 license = {text = "MIT"}

packages/agent-governance-dotnet/src/AgentGovernance/AgentGovernance.csproj

@@ -4,7 +4,7 @@
     <TargetFramework>net8.0</TargetFramework>
     <RootNamespace>AgentGovernance</RootNamespace>
     <AssemblyName>AgentGovernance</AssemblyName>
-    <Version>1.1.0</Version>
+    <Version>2.1.0</Version>
     <Description>Agent Governance Toolkit — .NET SDK for policy enforcement, rate limiting, zero-trust identity, OpenTelemetry metrics, and audit logging for autonomous AI agents. Compatible with Microsoft Agent Framework and Semantic Kernel.</Description>
     <PackageId>Microsoft.AgentGovernance</PackageId>
     <Authors>Microsoft</Authors>

packages/agent-hypervisor/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agent-hypervisor"
-version = "2.0.2"
+version = "2.1.0"
 description = "Agent Hypervisor — Runtime supervisor for multi-agent Shared Sessions with Execution Rings, Joint Liability, Saga Orchestration, and hash-chained audit trails"
 readme = "README.md"
 license = "MIT"

packages/agent-lightning/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-lightning"
-version = "1.0.0"
+version = "2.1.0"
 description = "Agent-Lightning RL integration for the Agent Governance Toolkit — governed training with policy enforcement"
 readme = "README.md"
 license = {text = "MIT"}

packages/agent-marketplace/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-marketplace"
-version = "1.0.0"
+version = "2.1.0"
 description = "Plugin marketplace for the Agent Governance Toolkit — discover, install, verify, and manage plugins"
 readme = "README.md"
 license = {text = "MIT"}

packages/agent-mesh/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agentmesh-platform"
-version = "2.0.2"
+version = "2.1.0"
 description = "Community Edition — The Secure Nervous System for Cloud-Native Agent Ecosystems - Identity, Trust, Reward, Governance"
 readme = "README.md"
 license = {text = "MIT"}

packages/agent-mesh/sdks/typescript/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agentmesh/sdk",
-  "version": "0.1.0",
+  "version": "1.0.0",
   "description": "TypeScript SDK for AgentMesh \u2014 agent identity, trust scoring, policy evaluation, and audit logging",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

packages/agent-os/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agent-os-kernel"
-version = "2.0.2"
+version = "2.1.0"
 description = "Community Edition — A kernel architecture for governing autonomous AI agents with Nexus Trust Exchange"
 readme = "README.md"
 license = "MIT"