elsai Agents — Release Notes

v0.3.0

Release Date: Jul 2026

Upgrades Agent-to-Agent (A2A) support to A2A Protocol v1.0 via a2a-sdk>=1.0.0 (tested with 1.1.0). Adds the shared sandbox execution model for isolated workspace runs. See Agent-to-Agent (A2A) and Sandbox.

A2A Protocol v1.0

a2a-sdk 1.x — server and client now target a2a-sdk>=1.0.0,<2.0.0 (previously 0.3.x)
High-level API unchanged — A2AServer, A2AAgent, as_tool(), and Graph integration work as before for typical usage
Compliant streaming by default — enable_a2a_compliant_streaming=True sends artifact updates per the v1 spec
client_config — pass a2a.client.ClientConfig to A2AAgent for authenticated endpoints (replaces deprecated a2a_client_factory)
Stream normalizer — iter_normalized_responses and A2AStreamNormalizer exported from elsai.multiagent.a2a for custom v1 clients
Session isolation — per-context_id agent pooling with configurable max_active_contexts and strict_tool_policy
v0.3 backward compatibility — set enable_v0_3_compat=True on A2AServer for legacy wire-format clients

Shared sandbox execution (`elsai-agents`)

Sandbox — application-owned workspace with start/stop, flush, attach/detach, and read_write / read_only attach modes
AgentConfig(sandbox=...) — multiple agents share one filesystem in-process while keeping separate conversations
SandboxPlugin — registers workspace tools: execute, read_file, write_file, list_dir (auto-added on attach when sandbox= is set)
SandboxManager — get-or-create sessions keyed by workspace_id, with idle TTL backstop via cleanup_expired()
Host tool blocking — in SandboxMode.SANDBOX, host prebuilt tools (shell, python_repl, file_read, file_write, environment) are blocked; use sandbox plugin tools instead
Plugin helpers — run_command, read_workspace_file, write_workspace_file, list_workspace_dir for custom @tool functions
Structured audit events — lifecycle and mutation logging on elsai.sandbox.audit

Sandbox backends ship in elsai-agents-tools 0.2.0: LocalSandboxBackend (dev), AgentCoreSandboxTemplate (production), DaytonaSandboxTemplate (remote). See Sandbox backends.

Breaking changes (raw HTTP / third-party clients only)

If you call an Elsai A2A server with raw HTTP or a third-party v0.3 client, you must either migrate to the v1 wire format (SendMessage, A2A-Version: 1.0 header) or enable enable_v0_3_compat=True on the server. Elsai SDK users (A2AAgent / A2AServer) are not affected.

See Migrating from A2A v0.3.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.3.0
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents-tools==0.3.0

With A2A support:

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents[a2a]==0.3.0"

Sandbox backends (optional extras):

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents-tools[agent-core-code-interpreter]==0.3.0"
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents-tools[sandbox-daytona]==0.3.0"

Documentation

Sandbox — Overview — workspace model, TTL, backends
Sandbox — Shared workspace — multi-agent attach and detach
Sandbox API — Sandbox, SandboxManager, SandboxPlugin
Agent-to-Agent (A2A) — A2A Protocol v1.0 migration

v0.2.1

Release Date: June 2026

Bugfix release for A2A session isolation — stateful tools and conversation history no longer leak across concurrent context_id values on the same A2AServer.

A2A session isolation (`elsai-agents`)

A2ASessionStore — One Agent + SessionManager per A2A context_id.
Agent factory mode — Pass a callable (A2AContextContext) -> Agent for per-context custom configuration.
Default storage — FileSessionManager under $ELSAI_A2A_SESSION_DIR/<context_id>/.
max_active_contexts — LRU eviction of in-memory context agents (default 100); in-flight contexts are protected.
strict_tool_policy — Fail startup when warnlisted tools are not PER_CONTEXT-safe.
A2AToolSessionScope — SHARED, CONTEXT_KEYED, and PER_CONTEXT tiers for custom tools.
A2ASessionStoreMetrics — cache_hits, cache_misses, and evictions for observability.

Stateful prebuilt tools (`elsai-agents-tools`)

Prebuilt tools now declare PER_CONTEXT scope and implement clone_for_a2a_context() so mutable state does not leak across A2A context_id values:

Tool	Per-context state
`python_repl`	REPL namespace + pickle under `…/<context_id>/repl/`
`shell`	Default `work_dir` under `…/<context_id>/shell/`
`use_computer`	Screenshots under `…/<context_id>/use_computer/screenshots/`
`code_interpreter`	Sandboxed sessions namespaced by `context_id` (`AgentCoreCodeInterpreter`)
`browser`	Browser profile under `…/<context_id>/browser/user_data/` (`LocalChromiumBrowser`, `AgentCoreBrowser`)
`mcp_client`	In-process MCP connection pool per context
`graph`	Graph IDs prefixed with `context_id`
`workflow`	Workflow files under `…/<context_id>/workflows/`
`mem0_memory`	FAISS store under `…/<context_id>/mem0/faiss/`

python_repl additionally replaces the former process-wide global REPL singleton with PythonReplTool. Registry name stays python_repl.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.2.1
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents[a2a]==0.2.1"
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents-tools==0.1.0

Documentation

Agent-to-Agent (A2A) — session isolation, S3 production, tool policy, operator table
A2A API — A2AServer, A2ASessionStore, handler options
Sessions — A2A sessions — file and S3 backing per context_id
Prebuilt tools — Environment variables — tool configuration env vars

Environment variables

Variable	Description
`ELSAI_A2A_SESSION_DIR`	Root for A2A session files and on-disk tool state
`PYTHON_REPL_PERSISTENCE_DIR`	Standalone `python_repl` persistence root
`A2A_SESSIONS_BUCKET`	S3 bucket for production A2A sessions (deployment convention)
`A2A_SESSIONS_PREFIX`	S3 key prefix for A2A contexts
`A2A_PUBLIC_URL`	Public URL for the agent card

Full reference: A2A — Environment variables.

v0.2.0

Release Date: Jun 2026

Compatible with elsai-model v2.0.0 from elsai Core.

elsai-agents now works with the unified *Model provider API. Pass any supported model directly to the agent:

python

agent = Agent(model=OpenAIModel(...))

Supported providers include OpenAI, Azure OpenAI, Amazon Bedrock, Anthropic, Gemini, LiteLLM, Ollama, Mistral, Writer, Meta Llama API, llama.cpp, OpenAI Responses, and SageMaker. See Model Providers.

Migration from connector API

If you used OpenAIConnector, BedrockConnector, or GeminiService, see the migration table in Core release notes.

Agent-as-tool concurrency modes

Agent.as_tool(mode=...) — control parallel invocation when the same sub-agent tool is called twice in one turn:
- reject (default) — fail fast with Agent '…' is already processing a request
- queue — wait until the shared agent is free
- spawn — isolated worker per call (parallel-safe)
AgentAsToolMode exported from elsai.agent
Built-in plugins and conversation managers support spawn cloning via supports_spawn() / clone_for_spawn()
tools=[researcher] auto-wraps with mode="reject"; non-default modes require an explicit .as_tool(mode=...)

See Agent as Tool.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.2.0

Optional extras:

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents[a2a]==0.2.0"
pip install --extra-index-url https://core-packages.elsai.ai/root/elsai-model/ elsai-model==2.0.0

v0.1.0

Release Date: 2026

Initial release of the elsai Agent Framework, built on the Strands Agents SDK.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.1.0

Optional extras:

bash

# With A2A support
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents[a2a]==0.1.0"

Core agent runtime

Agent class — Single entry point for creating and running agents with any supported LLM
Agent loop — Automatic tool-call/response cycle with configurable max iterations
Streaming — Token-by-token and event-stream output
Structured output — Typed responses via Pydantic models

Tools

@tool decorator — Convert any Python function into an agent tool
MCP Tools — Connect agents to any MCP server
Directory tools — Auto-load tools from ./tools/

Multi-agent

Graph — DAG-based agent pipelines with conditional routing
Swarm — Dynamic agent handoffs with shared context
Workflow — Sequential and parallel agent pipelines
Agent as Tool — Nest agents inside other agents
Agent-to-Agent (A2A) — Remote agent calls over HTTP via A2AServer and A2AAgent

Memory and sessions

SessionManager — Persist and restore agent conversation state across runs
File and S3 storage backends for session persistence

Lifecycle and control

Hooks — BeforeAgentCallEvent, AfterAgentCallEvent, BeforeToolCallEvent, AfterToolCallEvent
Interrupts — Pause and resume agent execution mid-loop
Retry strategies — ModelRetryStrategy with exponential backoff

Plugins

AgentSkills — Load reusable skill sets from SKILL.md files
AgentsMdPlugin — Hierarchical AGENTS.md discovery and system-prompt injection (cached at init; default keeps 3 nearest ancestor files)
LLMSteeringHandler — Pre/post-call LLM guardrails (Proceed / Guide / Interrupt)
ContextOffloader — Automatic offloading of large context to external storage

Agent configuration

Pass plugins, hooks, session_manager, agent_id, and other metadata through AgentConfig — direct Agent(...) keyword arguments for these fields are deprecated

elsai-agents-tools v0.3.0

Release Date: Jul 2026

write_todos — session task tracking on agent.state["todos"] for complex multi-step agent work; distinct from the disk-based journal tool. See Agents and Workflows API.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents-tools==0.3.0

Requires elsai-agents>=0.3.0.

elsai-agents-tools v0.2.0

Release Date: Jul 2026

Companion release for elsai-agents 0.3.0:

Sandbox backends — AgentCoreSandboxTemplate ([agent-core-code-interpreter]), DaytonaSandboxTemplate ([sandbox-daytona]), plus LocalSandboxBackend in elsai-agents for local dev. See Sandbox backends.
A2A client tools — A2AClientToolProvider, a2a_discover_agent, a2a_send_message upgraded to A2A Protocol v1.0 via a2a-sdk>=1.0.0. Public tool API unchanged.

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents-tools==0.2.0
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents-tools[a2a-client]==0.2.0"
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents-tools[agent-core-code-interpreter]==0.2.0"
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ "elsai-agents-tools[sandbox-daytona]==0.2.0"

Requires elsai-agents>=0.3.0 for sandbox execution and elsai-agents[a2a]>=0.3.0 when using A2A client tools.

elsai-agents-tools v0.1.0

Release Date: 2026

Initial release of the elsai Prebuilt Tools package — a Python companion to elsai-agents that ships ready-made agent tools for file I/O, shell access, web search, AWS integrations, multi-agent orchestration, and more. Import namespace: elsai_tools.

Installation

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents-tools==0.1.0

Requires Python 3.10+ and elsai-agents>=0.2.1.

Optional extras:

bash

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ \
  "elsai-agents-tools[mem0-memory,local-chromium-browser,diagram]==0.1.0"

What's included

Tool categories (base package)

RAG and memory — retrieve, memory, agent_core_memory, mem0_memory, elasticsearch_memory, mongodb_memory
File operations — editor, file_read, file_write
Shell and system — environment, shell, cron, use_computer
Code interpretation — python_repl, code_interpreter
Web and network — http_request, slack, browser, tavily_*, exa_*, mcp_client, rss, and more
Multimodal — generate_image, image_reader, speak, diagram, chat_video, search_video
AWS services — use_aws
Utilities — calculator, current_time, load_tool, sleep, stop
Agents and workflows — graph, swarm, workflow, batch, a2a_*

Class-based tool providers

LocalChromiumBrowser / AgentCoreBrowser — Browser automation
AgentCoreCodeInterpreter — Sandboxed code execution on Bedrock AgentCore
AgentCoreMemoryToolProvider — Bedrock AgentCore Memory
A2AClientToolProvider — Agent-to-Agent client tools

Registration model

Function tools — from elsai_tools.<module> import <tool> then Agent(tools=[...])
Class-based tools — instantiate provider, register .code_interpreter, .browser, or *provider.tools
Direct invocation — agent.tool.<name>(...) bypasses the LLM

Optional pip extras

Extras gate optional dependencies: mem0-memory, elasticsearch-memory, mongodb-memory, local-chromium-browser, agent-core-browser, agent-core-code-interpreter, rss, use-computer, diagram, twelvelabs, a2a-client.

A2A session isolation (requires elsai-agents 0.2.1+)

Stateful prebuilt tools declare PER_CONTEXT scope for multi-tenant A2A servers: python_repl, shell, use_computer, code_interpreter, browser, mcp_client, graph, workflow, mem0_memory. See Stateful tools on A2A.

Sensitive tools prompt for user confirmation before running. Set BYPASS_TOOL_CONSENT=true to skip prompts in CI or automated environments.

Documentation

Prebuilt Tools guide
Prebuilt Tools API
AI Editor Setup — Cursor, Copilot, and Claude Code configs for elsai_tools imports

elsai Agents — Release Notes ​

v0.3.0 ​

A2A Protocol v1.0 ​

Shared sandbox execution (elsai-agents) ​

Breaking changes (raw HTTP / third-party clients only) ​

Installation ​

Documentation ​

v0.2.1 ​

A2A session isolation (elsai-agents) ​

Stateful prebuilt tools (elsai-agents-tools) ​

Installation ​

Documentation ​

Environment variables ​

v0.2.0 ​

Migration from connector API ​

Agent-as-tool concurrency modes ​

Installation ​

v0.1.0 ​

Installation ​

Core agent runtime ​

Tools ​

Multi-agent ​

Memory and sessions ​

Lifecycle and control ​

Plugins ​

Agent configuration ​

elsai-agents-tools v0.3.0 ​

Installation ​

elsai-agents-tools v0.2.0 ​

elsai-agents-tools v0.1.0 ​

Installation ​

What's included ​

Tool categories (base package) ​

Class-based tool providers ​

Registration model ​

Optional pip extras ​

A2A session isolation (requires elsai-agents 0.2.1+) ​

Tool consent ​

Documentation ​

elsai Agents — Release Notes

v0.3.0

A2A Protocol v1.0

Shared sandbox execution (`elsai-agents`)

Breaking changes (raw HTTP / third-party clients only)

Installation

Documentation

v0.2.1

A2A session isolation (`elsai-agents`)

Stateful prebuilt tools (`elsai-agents-tools`)

Installation

Documentation

Environment variables

v0.2.0

Migration from connector API

Agent-as-tool concurrency modes

Installation

v0.1.0

Installation

Core agent runtime

Tools

Multi-agent

Memory and sessions

Lifecycle and control

Plugins

Agent configuration

elsai-agents-tools v0.3.0

Installation

elsai-agents-tools v0.2.0

elsai-agents-tools v0.1.0

Installation

What's included

Tool categories (base package)

Class-based tool providers

Registration model

Optional pip extras

A2A session isolation (requires elsai-agents 0.2.1+)

Tool consent

Documentation