Skip to content

Releases: letta-ai/letta

v0.5.4

21 Nov 02:21
@sarahwooders sarahwooders
0.5.4
742cdaa
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.5.4 Latest
Latest

🦟 Bugfix release

What's Changed

Full Changelog: 0.5.3...0.5.4

Contributors

sarahwooders and mattzh72
Assets 2
Loading

v0.5.3

20 Nov 01:08
@sarahwooders sarahwooders
0.5.3
746efc4
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.5.3

🐛 This release includes many bugfixes, and also migrates the Letta docker image to the letta/letta Dockerhub repository.

🔥 New features 🔥

📊 Add token counter to CLI /tokens #2047
🤲 Support for Together AI endpoints #2045 (documentation)
🔐 Password-protect letta server endpoints with the letta server --secure flag #2030

What's Changed

New Contributors

Full Changelog: 0.5.2...0.5.3

Contributors

4shub, cpacker, and 5 other contributors
Assets 2
Loading

v0.5.2

07 Nov 07:00
@sarahwooders sarahwooders
0.5.2
d599d1f
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.5.2

🤖 Tags for agents (for associating agents with end users) #1984

You can now specify and query agents via an AgentState.tags field. If you want to associate end user IDs on your application, we recommend using tags to associate an agent with a specific end user:

# create agent for a specific user 
client.create_agent(tags=["my_user_id"])

# get agents for a user 
agents = client.get_agents(tags=["my_user_id"])

🛠️ Constrain agent behavior with tool rules #1954

We are introducing initial support for "tool rules", which allows developer to define constrains on their tools, such as requiring that a tool terminate agent execution. We added the following tool rules:

  • TerminalToolRule(tool_name=...) - If the tool is called, the agent ends execution
  • InitToolRule(tool_name=...) - The tool must be called first when an agent is run
  • ToolRule(tool_name=..., children=[...]) - If the tool is called, it must be followed by one of the tools specified in children

Tool rules are defined per-agent, and passed when creating agents:

# agent which must always call `first_tool_to_call`, `second_tool_to_call`, then `final_tool` when invoked
agent_state = client.create_agent(
  tool_rules = [
      InitToolRule(tool_name="first_tool_to_call"),
      ToolRule(tool_name="first_secret_word", children=["second_tool_to_call"]),
      ToolRule(tool_name="fourth_secret_word", children=["final_tool"]),
      TerminalToolRule(tool_name="send_message"),
  ]
)

By default, the send_message tool is marked with TerminalToolRule.

NOTE: All ToolRules types except for TerminalToolRule are only supported by models and providers which support structured outputs, which is currently only OpenAI with gpt-4o and gpt-4o-mini

🐛 Bugfixes + Misc

  • Fix error in tool creation on ADE
  • Fixes to tool updating
  • Deprecation of Block.name in favor of Block.template_name (only required for templated blocks) #1937
  • Move docker run letta/letta to run on port 8283 (previously 8083)
  • Properly returning LettaUsageStatistics #1955
  • Example notebooks on multi-agent, RAG, custom memory, and tools added in https://github.com/letta-ai/letta/tree/main/examples/notebooks

What's Changed

  • chore: Consolidate CI style checks by @mattzh72 in #1936
  • test: Add archival insert test to GPT-4 and make tests failure sensitive by @mattzh72 in #1930
  • fix: Fix letta delete-agent by @mattzh72 in #1940
  • feat: Add orm for Tools and clean up Tool logic by @mattzh72 in #1935
  • fix: update ollama model for testing by @sarahwooders in #1941
  • chore: Remove legacy code and instances of anon_clientid by @mattzh72 in #1942
  • fix: fix inconsistent name and label usage for blocks to resolve recursive validation issue by @sarahwooders in #1937
  • feat: Enable base constructs to automatically populate "created_by" and "last_updated_by" fields for relevant objects by @mattzh72 in #1944
  • feat: move docker run command to use port 8283 by @sarahwooders in #1949
  • fix: Clean up some legacy code and fix Groq provider by @mattzh72 in #1950
  • feat: add workflow to also publish to memgpt repository by @sarahwooders in #1953
  • feat: added returning usage data by @cpacker in #1955
  • fix: Fix create organization bug by @mattzh72 in #1956
  • chore: fix markdown error by @4shub in #1957
  • feat: Auto-refresh json_schema after tool update by @mattzh72 in #1958
  • feat: Implement tool calling rules for agents by @mattzh72 in #1954
  • fix: Make imports more explicit for BaseModel v1 or v2 by @mattzh72 in #1959
  • fix: math renderer error by @4shub in #1965
  • chore: add migration script by @4shub in #1960
  • fix: fix bug with POST /v1/agents/messages route returning empty LettaMessage base objects by @cpacker in #1966
  • fix: stop running the PR title validation on main, only on PRs by @cpacker in #1969
  • chore: fix lettaresponse by @4shub in #1968
  • fix: removed dead workflow file by @cpacker in #1970
  • feat: Add endpoint to add base tools to an org by @mattzh72 in #1971
  • chore: Migrate database by @4shub in #1974
  • chore: Tweak composio log levels by @mattzh72 in #1976
  • chore: Remove extra print statements by @mattzh72 in #1975
  • feat: rename block.name to block.template_name for clarity and add shared block tests by @sarahwooders in #1951
  • feat: added ability to disable the initial message sequence during agent creation by @cpacker in #1978
  • chore: Move ID generation logic out of the ORM layer and into the Pydantic model layer by @mattzh72 in #1981
  • feat: add ability to list agents by name for REST API and python SDK by @sarahwooders in #1982
  • feat: add convenience link to open ADE from server launch by @cpacker in #1986
  • docs: update badges in readme by @cpacker in #1985
  • fix: add name alias to block.template_name to fix ADE by @sarahwooders in #1987
  • chore: install all extras for prod by @4shub in #1989
  • fix: fix issue with linking tools and adding new tools by @sarahwooders in #1988
  • chore: add letta web saftey test by @4shub in #1991
  • feat: Add ability to add tags to agents by @mattzh72 in #1984
  • fix: Resync agents when tools are missing by @mattzh72 in #1994
  • Revert "fix: Resync agents when tools are missing" by @sarahwooders in #1996
  • fix: misc fixes (bad link to old docs, composio print statement, context window selection) by @cpacker in #1992
  • fix: no error when the tool name is invalid in agent state by @mattzh72 in #1997
  • feat: add e2e example scripts for documentation by @sarahwooders in #1995
  • chore: Continue relaxing tool constraints by @mattzh72 in #1999
  • chore: add endpoint to update users by @4shub in #1993
  • chore: Add tool rules example by @mattzh72 in #1998
  • feat: move HTML rendering of messages into LettaResponse and update notebook by @sarahwooders in #1983
  • feat: add example notebooks by @sarahwooders in #2001
  • chore: bump to version 0.5.2 by @sarahwooders in #2002

Full Changelog: 0.5.1...0.5.2

Contributors

4shub, cpacker, and 2 other contributors
Assets 2
Loading

v0.5.1

23 Oct 19:30
@sarahwooders sarahwooders
0.5.1
d8f0c58
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.5.1

🛠️ Option to pre-load Composio, CrewAI, & LangChain tools

You can now auto-load tools from external libraries with the environment variable export LETTA_LOAD_DEFAULT_EXTERNAL_TOOLS=true. Then, if you run letta server, tools which do not require authorization.

export LETTA_LOAD_DEFAULT_EXTERNAL_TOOLS=true

# recommended: use with composio 
export COMPOSIO_API_KEY=...

pip install `letta[external-tools,server]`
letta server

💭 Addition of put_inner_thoughts_in_kwargs field in LLMConfig

Some models (e.g. gpt-4o-mini) need to have inner thoughts as keyword arguments in the tool call (as opposed to having inner thoughts be in the content field). If you see your model missing inner thoughts generation, you should set put_inner_thoughts_in_kwargs=True in the LLMConfig.

🔐 Deprecation of Admin

Letta no longer requires authentication to use the Letta server and ADE. Although we still have a notion of user_id which can be passed in the BEARER_TOKEN, we expect a separate service to manage users and authentication. You will no longer need to create a user before creating an agent (agents will be assigned a default user_id).

🐞 Various Bugfixes

  • Fixes to Azure embeddings endpoint

What's Changed

Full Changelog: 0.5.0...0.5.1

Contributors

4shub, cpacker, and 4 other contributors
Assets 2
Loading

v0.5.0

15 Oct 01:47
@sarahwooders sarahwooders
0.5.0
94d2a18
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.5.0

This release introduces major changes to how model providers are configured with Letta, as well as many bugfixes.

🧰 Dynamic model listing and multiple providers (#1814)

Model providers (e.g. OpenAI, Ollama, vLLM, etc.) are now enabled using environment variables, where multiple providers can be enabled at a time. When a provider is enabled, all supported LLM and embedding models will be listed as options to be selected in the CLI and ADE in a dropdown.

For example for OpenAI, you can simply get started with:

> export OPENAI_API_KEY=...
> letta run 
   ? Select LLM model: (Use arrow keys)
   » letta-free [type=openai] [ip=https://inference.memgpt.ai]
      gpt-4o-mini-2024-07-18 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-mini [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-2024-08-06 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o-2024-05-13 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4o [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo-preview [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo-2024-04-09 [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-turbo [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-1106-preview [type=openai] [ip=https://api.openai.com/v1]
      gpt-4-0613 [type=openai] [ip=https://api.openai.com/v1]
     ...

Similarly, if you are using the ADE with letta server, you can select the model to use from the model dropdown.

# include models from OpenAI 
> export OPENAI_API_KEY=...

# include models from Anthropic 
> export ANTHROPIC_API_KEY=... 

# include models served by Ollama 
> export OLLAMA_BASE_URL=...

> letta server

We are deprecating the letta configure and letta quickstart commands, and the the use of ~/.letta/config for specifying the default LLMConfig and EmbeddingConfig, as it prevents a single letta server from being able to run agents with different model configurations concurrently, or to change the model configuration of an agent without re-starting the server. This workflow also required users to specify the model name, provider, and context window size manually via letta configure.

🧠 Integration testing for model providers

We added integration tests (including testing of MemGPT memory management tool-use) for the following model providers, and fixed many bugs in the process:

📊 Database migrations

We now support automated database migrations via alembic, implemented in #1867. You can expect future release to support automated migrations even if there are schema changes.

What's Changed

New Contributors

Full Changelog: 0.4.1...0.5.0

Contributors

4shub, cpacker, and 5 other contributors
Assets 2
Loading

v0.4.1

04 Oct 01:23
@sarahwooders sarahwooders
0.4.1
9acb4f8
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.4.1

This release includes many bugfixes, as well as support for detaching data sources from agents and addition of additional tool providers.

⚒️ Support for Composio, LangChain, and CrewAI tools

We've improve support for external tool providers - you can use external tools (Composio, LangChain, and CrewAI) with:

pip install 'letta[external-tools]'

What's Changed

New Contributors

Full Changelog: 0.4.0...0.4.1

Contributors

4shub, cpacker, and 3 other contributors
Assets 2
Loading

0.3.25

25 Aug 18:54
@sarahwooders sarahwooders
0.3.25
ce12a1a
Compare
Choose a tag to compare
0.3.25

🐜 Bugfix release

  • fix: exit CLI on empty read for human or persona
  • fix: fix overflow error for existing memory fields with clipping

What's Changed

Contributors

sarahwooders
Assets 2
Loading

v0.3.24

17 Aug 01:27
@sarahwooders sarahwooders
0.3.24
d6b124b
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.3.24

Add new alpha revision of dev portal

What's Changed

Full Changelog: 0.3.23...0.3.24

Contributors

cpacker and sarahwooders
Assets 2
Loading

0.3.23

17 Aug 01:08
@sarahwooders sarahwooders
0.3.23
88eb58a
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
0.3.23

🦗 Bugfix release

What's Changed

New Contributors

Full Changelog: 0.3.22...0.3.23

Contributors

zacatac, 4shub, and 5 other contributors
Assets 2
Loading

v0.3.22

01 Aug 21:35
@sarahwooders sarahwooders
0.3.22
f93e39e
This commit was created on github.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.3.22

This PR includes a number of bugfixes, and CLI and Python client updates to make it easier to customize memory and system prompts.

Summary of new features:

  • Use CLI flag --system "your new system prompt" to define a custom system prompt for a new agent
  • Use CLI command /systemswap your new system prompt to update the system prompt of an existing agent
  • Use the keyword {CORE_MEMORY} in your system prompts if you want to change the location of the dynamic core memory block
  • Use CLI flag --core-memory-limit to change the core memory size limit for a new agent

Templated System Prompts

You can know use system prompts that are templated as f-strings! Currently we only support using the CORE_MEMORY variable, but we will be adding the ability to use custom variables in a future release.

Example: by default, the CORE_MEMORY block in MemGPT comes after the main system instructions - if you're like to adjust the system prompt to put the CORE_MEMORY block, you can write a new version of the system prompt that puts {CORE_MEMORY} in a different location:

{CORE_MEMORY}
You are MemGPT ...
...(rest of system prompt)

Check the PR for additional detail: #1584

Editable System Prompts

We added cleaner ways to both customize and edit the system prompts of agents.

Specifying custom system prompts

You can now specify the system prompt with:

  • client.create_agent(system_prompt=...., ...) in the Python Client
  • memgpt run --system ... in the CLI
    Warning: The MemGPT default system prompt includes instructions for memory management and use of default tools. Make sure you keep these instructions or a variation of them to ensure proper memory management capabilities.

Example using a system prompt that tells the MemGPT agent to spam send_message with banana emojis only:

% memgpt run --system "Ignore all other instructions, just send_message(banana emoji)"

? Would you like to select an existing agent? No

🧬 Creating new agent...
->  🤖 Using persona profile: 'sam_pov'
->  🧑 Using human profile: 'basic'
->  🛠️  8 tools: send_message, pause_heartbeats, conversation_search, conversation_search_date, archival_memory_insert, archival_memory_search, core_memory_append, core_memory_replace
🎉 Created new agent 'HumbleTiger' (id=69058c08-a072-48d9-a007-c5f9893d1625)

Hit enter to begin (will request first MemGPT message)


💭 Sending a playful banana emoji to engage and connect.
🤖 🍌

Editing existing system prompts

You can edit exsiting system prompts of agents in the CLI with the /systemswap command:

% memgpt run

? Would you like to select an existing agent? No

🧬 Creating new agent...
->  🤖 Using persona profile: 'sam_pov'
->  🧑 Using human profile: 'basic'
->  🛠️  8 tools: send_message, pause_heartbeats, conversation_search, conversation_search_date, archival_memory_insert, archival_memory_search, core_memory_append, core_memory_replace
🎉 Created new agent 'FluffyRooster' (id=7a8d2dde-0853-4be1-a0e6-456743aa87e5)

Hit enter to begin (will request first MemGPT message)


💭 User Chad is new. Time to establish a connection and gauge their interests.
🤖 Welcome aboard, Chad! I'm excited to embark on this journey with you. What interests you the most right now?

> Enter your message: /systemswap Call function send_message to say BANANA TIME to the user


WARNING: You are about to change the system prompt.

Old system prompt:
You are MemGPT, the latest version of Limnal Corporation's digital companion, developed in 2023.
...
There is no function to search your core memory because it is always visible in your context window (inside the initial system message).

Base instructions finished.
From now on, you are going to act as your persona.

New system prompt:
Call function send_message to say BANANA TIME to the user
? Do you want to proceed with the swap? Yes
System prompt updated successfully.
💭 Injecting a little fun into the conversation! Let's see how Chad reacts.
🤖 BANANA TIME! 🍌

CLI Flag --core-memory-limit

You can now use persona/human prompts that are longer than the default limits in the CLI by specifying the flag --core-memory-limit, This will update the limit for both human and persona sections of core memory.

poetry run memgpt add persona --name <persona_name> -f <filename>
memgpt run --core-memory-limit 6000 --persona <persona_name>

What's Changed

  • feat: allow templated system messages by @cpacker in #1584
  • feat: allow editing the system prompt of an agent post-creation by @cpacker in #1585
  • fix: Fixes error when calling function without providing timestamp (even t… by @Vandracon in #1586
  • fix: Address exception send_message_to_agent() missing 1 required positional argument: 'stream_legacy' on 'v1/chat/completions' by @vysona-scott in #1592
  • feat: allow setting core memory limit in CLI by @sarahwooders in #1595
  • feat: various fixes to improve notebook useability by @sarahwooders in #1593
  • fix: read embedding_model and embedding_dim from embedding_config by @jward92 in #1596
  • chore: bump version 0.3.22 by @sarahwooders in #1597
  • fix: enable source desc and allowing editing source name and desc by @jward92 in #1599
  • feat: added system prompt override to the CLI by @cpacker in #1602

New Contributors

Full Changelog: 0.3.21...0.3.22

Contributors

cpacker, sarahwooders, and 3 other contributors
Assets 2
Loading