Mistral Vibe (Remote Agents) + Mistral Medium 3.5
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5
Vibe is Mistral's cloud-hosted coding-agent platform: each session runs in an isolated sandbox with task state, history, and approvals. Spawnable from CLI or Le Chat, with parallel execution. Local CLI sessions can be "teleported" to the cloud and resumed. Powered by Mistral Medium 3.5 (77.6% SWE-Bench Verified). Plugs into GitHub, Linear/Jira, Sentry, Slack/Teams.
At a glance
- Type
- Cloud-hosted async coding agents with teleportable session state
- Tier
- T1
- Section
- Coding-agent memory
- Created
- 2026-05-02 (Vibe + Medium 3.5 launch)
- Latest release
- Medium 3.5 weights on Hugging Face (modified MIT); Vibe service closed
- License
- Modified MIT (Medium 3.5 weights); Vibe service closed
- GitHub
- not applicable — no GitHub repo for Vibe (model on HF; service closed)
- Pricing
- API: $1.5/M input tokens; $7.5/M output tokens (Medium 3.5); Vibe via Pro/Team/Enterprise plans
- Funding
- $2.71B total raised; Series C €1.7B (ASML lead) Sep 2025; $830M debt Mar 2026
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- cross-session
- update
- append-only
- unit
- episode
- governance
- opaque
- conflict
- none
When to use
Optimised for: async parallel coding agents with teleportable session state; SWE-Bench-leading model (77.6%); EU-jurisdiction stack
Anti-fit: not for non-Mistral stacks; not for users requiring full transparency of memory eviction policy; not for offline/air-gapped use
Pros & cons
Pros
Async parallel coding agents with teleportable session state; broad ecosystem integrations (GitHub/Linear/Jira/Sentry); SWE-Bench-leading model; weights open; EU-jurisdiction stack.
Cons
Vibe service closed; SWE-Bench claim is vendor self-report; no third-party reproduction yet; pricing tied to Pro/Team/Enterprise tiers; opaque memory eviction policy.
Claims & capabilities
Mistral Medium 3.5: 77.6% SWE-Bench Verified; 91.4 on τ³-Telecom (agentic)
Technical surface
- API surface
- REST + CLI (Mistral CLI) + Le Chat web; SDK Python/JS
- Backend storage
- custom (Mistral-managed sandboxes)
- Deployment
- Managed cloud (la Plateforme + Le Chat) + NVIDIA NIM containers
- Embedding model
- Mistral embed-v2 (default; multiple supported)
- Multi-tenancy
- hard-isolation (per-session sandbox)
- MCP
- native (first-party — Mistral Agents support MCP)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Mistral Vibe (Remote Agents) + Mistral Medium 3.5 with…
Similar systems
Other coding-agent memory in the catalog, ranked by inbound references.
- Aider T2
Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries static preferences.
- Augment Code T1
Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. MCP endpoint exposes the graph.
- Bolt.new (StackBlitz) T2
In-browser WebContainer (Rust-backed shared memory) is the implicit state store. No dedicated memory abstraction — project files are the state. Team plan adds shared workspaces + GitHub integration.
- Continue.dev Memory MCP T2
Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP rather than native to the Continue core. Scope depends on MCP server deployment (local or shared).
- Devin (Cognition) T1
Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads past session trajectories for self-improvement; writes notes for recurring scheduled tasks.
- Lovable T2
Long-term context stored as files in /docs that the agent reads on each session. Agent Mode (default since July 2025) holds working context within session but doesn't persist cross-session beyond filesystem state.
Related systems
References (1)
- Mistral Large 2 / Mixtral family depends on at runtime — adjacent-infrastructure cell: requires Mistral la Plateforme + Le Chat; integrates GitHub/Linear/Jira/Sentry/Slack/Teams; NVIDIA NIM containers for self-host