Stop onboarding your coding agents from scratch every session.

AICTX is a lightweight repo-local continuity runtime for Codex, Claude Code, GitHub Copilot, and other coding agents. It gives each new session the useful facts from the repository — what happened, what failed, what changed, what was decided, and what should happen next — without turning AICTX into an agent framework, task manager, vector database, or cloud memory product.

pip install aictx
aictx install
aictx init

After that, keep working normally. Compatible agents run the lifecycle themselves:

resume -> work -> finalize -> next session resumes

Quickstart · What AICTX writes · Continuity View · Website

Coding agents are strong, but new sessions still start cold:

• they rescan the same files and docs;
• they rediscover decisions already made;
• they repeat failed commands and stale assumptions;
• useful context gets trapped in one vendor's chat history.

AICTX turns that fragile chat-local memory into repo-local operational continuity. The next agent starts with a compact brief instead of guessing from scratch.

The user path is intentionally small:

aictx install
aictx init
then let the coding agent work

The agent path is equally small:

aictx resume --repo . --task "fix the parser bug" --json
# agent edits, tests, debugs, and reviews normally
aictx finalize --repo . --status success --summary "Fixed parser recovery and ran focused parser tests" --json

A later session resumes from local repository state instead of hidden chat history.

You: fix the parser bug
Agent: resumes repo-local continuity
Agent: works normally
Agent: finalizes factual evidence for the next session

AICTX records operational facts that make the next session useful faster:

Everything is local and inspectable. The default runtime writes under .aictx/ and generated agent-instruction files; no account, daemon, dashboard, or cloud sync service is required.

Generate an inspectable continuity report at any time:

aictx view --repo .

Default output:

.aictx/reports/continuity-view.md
.aictx/reports/continuity-map.mmd

Check health and repair guidance:

aictx doctor --repo . --json

AICTX is not hidden memory. It is reviewable repo-local continuity with explicit quality signals.

• Local-first: continuity belongs to the repository, not a private chat thread.
• Agent-neutral: Codex can leave context that Claude Code, Copilot, or another compatible agent can resume.
• Tiny default path: install, init, then work; manual resume/finalize commands are mostly for inspection and unsupported runners.
• Evidence-oriented: AICTX records what was observed, validated, skipped, or left unfinished.
• Honest by design: stale context is marked stale; missing validation stays visible; AICTX never claims automatic correctness.

AICTX is runner-aware, not runner-locked.

• Codex: AGENTS.md, optional global Codex setup, CLI/MCP lifecycle guidance.
• Claude Code: CLAUDE.md, Claude settings/hooks, CLI/MCP lifecycle guidance.
• GitHub Copilot: repository instructions and optional prompt files where supported.
• Generic agents: any runner that can read instructions and call CLI or MCP tools.

Compatible agents prefer AICTX MCP tools when available and fall back to the CLI:

aictx_resume / aictx_finalize
# or
aictx resume --repo . --task "<goal>" --json
aictx finalize --repo . --status success|failure --summary "<what happened>" --json

AICTX is not an autonomous coding agent, RAG system, vector database, task manager, dashboard, cloud memory service, replacement for tests/review, or guarantee of correctness, productivity gains, or token savings.

It is a lightweight continuity runtime that helps cooperating coding agents start from useful repository state.

Start here:

• Quickstart
• Installation
• Usage
• What AICTX writes
• Continuity View
• Doctor diagnostics

Core concepts:

• Technical overview
• Work State
• Handoffs and Decisions
• Failure Memory
• Execution Summary
• Execution Contracts

Advanced:

• MCP
• RepoMap
• Portability
• Continuity Guard
• Steer Guard
• Cleanup
• Safety
• Limitations

Legacy/internal compatibility surfaces are intentionally kept out of the first-run path; see Usage for the split between supported advanced commands and compatibility-only commands.

For the full command reference, see Usage.

• Website: https://aictx.org
• PyPI: https://pypi.org/project/aictx/
• CLI: aictx
• Official identity: docs/OFFICIAL_PROJECT.md