AGiXT Adaptive Memory
https://github.com/Josh-XT/AGiXT
Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction state, conversation history as unified agent state.
At a glance
- Type
- Adaptive provider-spanning + plugin storage
- Tier
- T2
- Section
- Framework-embedded memory
- Created
- 2023-04
- Latest release
- v1.9.4 2026-04-08
- License
- MIT
- GitHub
- 3.2k★ +15/mo Python
- Pricing
- OSS free (MIT); agixt.com offers hosted service but pricing not publicly listed
- Funding
- searched not found
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: provider-spanning + plugin storage
Anti-fit: not for enterprise-grade SLA workloads
Pros & cons
Pros
OSS adaptive memory with web-search fallback when local memory misses; multi-LLM support.
Cons
Smaller community; documentation uneven; production track record limited.
Claims & capabilities
Supports 20+ LLM providers. Community-maintained.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Both (OSS self-hosted; agixt.com managed cloud implied)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- LangGraph Persistence T2
Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.
- AutoGen Memory T2
ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Agno (Phidata) Memory T2
Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Botpress LLMz T1
Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.
- DSPy History T3
dspy.History primitive — typed field holding messages: list[dict] that slots into any Signature . No persistent memory of its own; purely a structured context-injection contract. DSPy's optimisation loop (MIPRO, BootstrapFewShot) treats historical turns as trainable few-shot structure.