MagicSchool
Teacher productivity platform (80+ teacher tools, 50+ student tools) for planning, differentiation, IEP generation, feedback. Does not maintain a cross-session learner model. Teachers input student context manually each session; district deployments can pre-populate fields via RAG over uploaded curriculum/policy documents.
At a glance
- Type
- Teacher tooling — no student-facing memory by design
- Tier
- T1
- Created
- 2023 (launched March-May 2023 by Adeel Khan; Denver CO)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- $15M total Series A · 2024-06
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- session
- update
- read-only
- unit
- document
- governance
- opaque
- conflict
- n/a
When to use
Optimised for: learner profile + spaced repetition + assessment-driven adaptation
Anti-fit: not for non-educational use cases
Pros & cons
Pros
Largest educator user base in this set; district-level RAG (curriculum + policy docs) is a practical and architecturally honest form of context persistence that does not require a student profile.
Cons
No student-facing memory or adaptive personalization — context is ephemeral and teacher-supplied each session; deliberate product choice but disqualifies meaningful student-memory classification.
Claims & capabilities
~6M educators. 40% of US public schools. 13,000+ schools/districts in 160+ countries. 77% of teachers report significantly improved quality of life.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Managed-only
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- no MCP support advertised — vertical product, no MCP server / client integration documented
- A2A
- no A2A protocol support advertised — vertical product, no A2A integration documented
- OpenTelemetry
- no OpenTelemetry integration advertised — vendor logs/observability not publicly documented
Similar systems
Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.
- NVIDIA ReMEmbR T3
Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).
- Abridge T1
Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.
- ASAPP GenerativeAgent T1
Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.
- BenevolentAI T1
Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop.
- Causaly T1
Drug discovery / target identification / causal mechanism tracing. The graph is the memory: 7 years of curated biomedical cause-effect relationships compounding with each new ingestion. Scientific RAG retrieves from a versioned causal substrate.
- Character.ai T1
Chat Memories (user-defined facts), auto-memories for c.ai+ subscribers, pinned memories, in-context retention. PipSqueak 2 model (April 2026) reduces in-conversation drift. Memory Visualization meter forthcoming.