Aider
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.
At a glance
- Type
- Per-repo chat history file + YAML config
- Tier
- T2
- Section
- Coding-agent memory
- Created
- 2023-05
- Latest release
- v0.86.0 2025-08-09
- License
- Apache-2.0
- GitHub
- 44.4k★ +1.7k/mo Python
- Pricing
- OSS
- Funding
- no public funding
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- cross-session
- update
- append-only
- unit
- episode
- governance
- user-controllable
- conflict
- none
When to use
Optimised for: simplicity / minimal config / per-repo chat history
Anti-fit: not for non-coding tasks; not for shared/team memory
Pros & cons
Pros
Most established CLI coding agent; explicit project-level conventions file + repo map keeps memory inspectable.
Cons
CLI-only — no IDE integration; memory is inspectable but not auto-learned.
Claims & capabilities
No vector store, no server-side persistence — file-only.
Technical surface
- API surface
- CLI (interactive REPL + /commands); no public REST/SDK
- Backend storage
- file (.aider.chat.history.md)
- Deployment
- Self-hostable
- Embedding model
- not applicable — uses LLMs not embeddings
- Multi-tenancy
- not applicable — CLI
- MCP
- no — uses CONVENTIONS.md instead
- A2A
- not supported
- OpenTelemetry
- no
Similar systems
Other coding-agent memory in the catalog, ranked by inbound references.
- 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.
- Mistral Vibe (Remote Agents) + Mistral Medium 3.5 T1
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.