Skip to content

Entry

Letta

Appears in 5 awesome lists

The MemGPT-lineage (arXiv 2310.08560, 1,000+ citations) stateful-agent platform — an OS-inspired memory hierarchy where the agent itself manages memory via tool calls: core memory (always in context, agent-editable — like RAM), recall (searchable history), and archival (long-term vector store).…

Open github.comletta-ai/letta

Found in these lists

Awesome Harness Engineering

Section: Memory & State · The reference architecture for stateful agents: three-tier memory (core / archival / recall) maps directly to harness state management design. Their agent loop redesign post is the most thorough public analysis of how memory structure shapes the harness.

FreshScore 93

Awesome LangChain

Section: Other LLM Frameworks · Platform for stateful agents with advanced memory that learn and self-improve

FreshScore 94

Awesome local LLM

Section: Memory Management · the stateful agents framework with memory, reasoning, and context management

FreshScore 90

Awesome Open Source AI

Section: 4. Agentic AI & Multi-Agent Systems · Platform for building stateful agents with advanced memory that learn and self-improve over time.

FreshScore 87

Awesome Prompts

Section: Agent Memory · The MemGPT-lineage (arXiv 2310.08560, 1,000+ citations) stateful-agent platform — an OS-inspired memory hierarchy where the agent itself manages memory via tool calls: core memory (always in context, agent-editable — like RAM), recall (searchable history), and archival (long-term vector store).…

FreshScore 96

mem0

The most-deployed memory layer for AI agents — drop-in add/search/update/delete fact storage with LLM-extracted long-term / short-term / semantic memory: automatic fact consolidation (dedup, contradiction resolution, decay) so agents keep "context that persists" without context bloat;…

In 14 listsDetails

LlamaIndex

(MIT) provides modules for structured outputs at different levels of abstraction, including output parsers for text completion endpoints, Pydantic programs for mapping prompts to structured outputs using function calling or output parsing, and pre-defined Pydantic programs for specific output types.

In 14 listsDetails

Haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search,…

In 13 listsDetails

promptfoo

🟢 — LLM eval + red-teaming/pentesting CLI with 50+ attack plugins (MIT). Note: OpenAI announced an acquisition agreement in March 2026; remains MIT-licensed — track governance. · updated 2026-10-13); Related: Promptfoo CI Action (checkout evaluation, not base/head diff; defaults to latest,…

In 13 listsDetails

AutoGen

Microsoft's multi-agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design.

In 14 listsDetails

DSPy

(MIT) is a framework for algorithmically optimizing LM prompts and weights. DSPy introduced typed predictor and signatures to leverage Pydantic for enforcing type constraints on inputs and outputs, improving upon string-based fields.

In 11 listsDetails

deja-vu

Indexes coding-agent sessions already written to disk and serves them back over MCP with no LLM calls, embeddings, or API keys. The zero-dependency binary solves the memory cold-start problem for cross-session persistence and demonstrates that agent memory can be built on existing filesystem…

In 11 listsDetails

Mastra

TypeScript-native agent framework (from the Gatsby team) with 22K+ stars and 300K+ weekly npm downloads. Connects to 40+ providers through one standard interface, with built-in workflows, RAG pipelines, and agent orchestration. The @mastra/deployer handles serverless deployment, and the eval…

In 12 listsDetails