Coding-agent memory

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. M…

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 …

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…

Memory under ~/.codex/memories/ : summaries, durable entries, recent-input logs, supporting evidence — generated in background after sessions go idle. Chronicle (opt-in macOS preview) uses screen-capture to seed memory. Off by default; o…

No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory rel…

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 stati…

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.

Discontinued: Continue was bought by Cursor (announced ~2026-06-16); the product is discontinued and the continuedev/continue repo is read-only. Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP rathe…

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.

Superseded: the sweepai/sweep README says the team now builds an AI coding assistant for JetBrains; the GitHub-app product described here is no longer the focus (repo not archived). No dedicated persistent memory layer. Operates as a Git…

Enterprise Context Engine builds a multi-dimensional knowledge graph from repos + CI/CD + PRs + tickets + docs at the org level. Individual completions stay session-scoped. Tabnine Agents (Nov 2025) adds team-shared agent context. Acquir…

Self-hosted persistent memory layer that captures coding-agent activity and recalls it in later sessions, positioned on public benchmark results. #7 in TeleAI Awesome-Agent-Memory

Dolt-backed, dependency-aware graph issue tracker that acts as persistent structured memory for coding agents, replacing markdown plans; `bd remember` stores durable facts and `bd prime` re-injects them.

MCP server + hooks that sandbox tool output out of the coding agent's context window (claims ~98% reduction) and persist session memory across 17 agent platforms.

Project-scoped memories in Cursor, created either by a background 'sidecar' model watching chats or by the agent via tool calls, and managed as auto-generated rules in settings. Traction: First-party feature of one of the most widely use…

Google's open-source Gemini CLI persists facts by editing tiered Markdown memory files — repo GEMINI.md, a per-project private memory folder and global ~/.gemini/GEMINI.md — that load into hierarchical context each session. Traction: Goo…

Repository-scoped memories that Copilot coding agent, code review and CLI write automatically, share across features, validate against the current code before use, and expire after 28 days; owners can review/delete them. Traction: Shippe…

Letta's stateful coding-agent harness: agents rewrite their own memory blocks and skills, version context in git via MemFS (syncable to GitHub) and reflect via a periodic /sleeptime 'dreaming' process. from Letta (MemGPT) team. letta-ai/…

Zilliz's persistent memory layer shared across agents like Claude Code and Codex: Markdown files are the source of truth, and Milvus indexes them for search. from the Milvus vendor

Codex Memories carries preferences, conventions and pitfalls across Codex threads as local memory files. The Chronicle research preview has been replaced by Computer History, a rebuilt macOS desktop feature (ChatGPT Pro, Business, Enterp…

LSP-backed MCP coding toolkit ('IDE for your agent') with a built-in project memory system for sharing knowledge across sessions, users and projects alongside AGENTS.md.